{ "checkedDate": "2026-10-25", "catalogCommit": "d006e5e0fec1b8e5b9debb85055fe506b17e08f2", "coverage": [ { "catalogId": "lotus", "catalogTitle": "Semantic Operators: A Declarative Model for Rich, AI-based Data Processing", "status": "included", "workId": "lotus", "source": "https://arxiv.org/abs/2407.11418v3" }, { "catalogId": "uqe", "catalogTitle": "UQE: A Query Engine for Unstructured Databases", "status": "included", "workId": "uqe", "source": "https://arxiv.org/abs/2407.09522v2" }, { "catalogId": "palimpzest", "catalogTitle": "A Declarative System for Optimizing AI Workloads", "status": "included", "workId": "palimpzest", "source": "https://arxiv.org/abs/2405.14696v2" }, { "catalogId": "docetl", "catalogTitle": "DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing", "status": "included", "workId": "docetl", "source": "https://arxiv.org/abs/2410.12189v3" }, { "catalogId": "suql", "catalogTitle": "SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models", "status": "included", "workId": "suql", "source": "https://arxiv.org/abs/2311.09818v2" }, { "catalogId": "sembench", "catalogTitle": "SemBench: A Benchmark for Semantic Query Processing Engines", "status": "included", "workId": "sembench", "source": "https://arxiv.org/abs/2511.01716v2" }, { "catalogId": "lrobench", "catalogTitle": "Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis", "status": "included", "workId": "lrobench", "source": "https://arxiv.org/abs/2603.02537v2" }, { "catalogId": "sema", "catalogTitle": "Sema: A High-performance System for LLM-based Semantic Query Processing", "status": "included", "workId": "sema", "source": "https://arxiv.org/abs/2603.11622v1" }, { "catalogId": "nousdb", "catalogTitle": "NousDB - A Fast Query Engine for Semantic Analytics", "status": "included", "workId": "nousdb", "source": "https://arxiv.org/abs/2610.28551v2" }, { "catalogId": "jevdb", "catalogTitle": "Prune First, Decide Fast: Scalable Semantic Query Processing with JEVDB", "status": "included", "workId": "jevdb", "source": "https://arxiv.org/abs/2610.02046v1" }, { "catalogId": "semviews", "catalogTitle": "Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries", "status": "included", "workId": "semviews", "source": "https://arxiv.org/abs/2610.12768v1" }, { "catalogId": "run-to-run-variance", "catalogTitle": "Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing", "status": "included", "workId": "run-to-run-variance", "source": "https://arxiv.org/abs/2610.13823v1" }, { "catalogId": "sembaker", "catalogTitle": "From Interpretation to Compilation: A Compilation-Based Execution Engine for Semantic Operator Systems", "status": "included", "workId": "sembaker", "source": "https://arxiv.org/abs/2608.06677v1" }, { "catalogId": "kalypso", "catalogTitle": "Kalypso: Relational LLM Serving", "status": "included", "workId": "kalypso", "source": "https://arxiv.org/abs/2607.23815v2" }, { "catalogId": "flockmtl", "catalogTitle": "Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB", "status": "included", "workId": "flockmtl", "source": "https://arxiv.org/abs/2504.01157v1" }, { "catalogId": "ipdb", "catalogTitle": "iPDB -- Optimizing Semantic SQL Queries", "status": "included", "workId": "ipdb", "source": "https://arxiv.org/abs/2601.16432v4" }, { "catalogId": "plop", "catalogTitle": "PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query Plans", "status": "included", "workId": "plop", "source": "https://arxiv.org/abs/2604.09944v2" }, { "catalogId": "relational-llm-optimization", "catalogTitle": "Optimizing LLM Queries in Relational Data Analytics Workloads", "status": "included", "workId": "relational-llm-optimization", "source": "https://arxiv.org/abs/2403.05821v2" }, { "catalogId": "llm-order-by", "catalogTitle": "Access Paths for Efficient Ordering with Large Language Models", "status": "included", "workId": "llm-order-by", "source": "https://arxiv.org/abs/2509.00303v5" }, { "catalogId": "larch", "catalogTitle": "Larch: Learned Query Optimization for Semantic Predicates", "status": "included", "workId": "larch", "source": "https://arxiv.org/abs/2606.07923v1" }, { "catalogId": "fast-semantic-filtering", "catalogTitle": "Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method", "status": "included", "workId": "fast-semantic-filtering", "source": "https://arxiv.org/abs/2606.08090v2" }, { "catalogId": "semjoin", "catalogTitle": "SemJoin: Semantic Join Optimization", "status": "included", "workId": "semjoin", "source": "https://arxiv.org/abs/2606.29532v1" }, { "catalogId": "uda-bench", "catalogTitle": "Unstructured Data Analysis using LLMs: A Comprehensive Benchmark", "status": "included", "workId": "uda-bench", "source": "https://arxiv.org/abs/2510.27119v1" }, { "catalogId": "spider2-aifunc", "catalogTitle": "Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows", "status": "included", "workId": "spider2-aifunc", "source": "https://arxiv.org/abs/2607.06229v1" }, { "catalogId": "vectorsqlbench", "catalogTitle": "Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL Queries", "status": "included", "workId": "vectorsqlbench", "source": "https://arxiv.org/abs/2506.23071v2" }, { "catalogId": "hybrid-deep-research", "catalogTitle": "Benchmarking Hybrid Deep Research Across Database Querying and Web Search", "status": "included", "workId": "hybrid-deep-research", "source": "https://arxiv.org/abs/2609.09410v1" }, { "catalogId": "stochastic-shift", "catalogTitle": "The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators", "status": "included", "workId": "stochastic-shift", "source": "https://arxiv.org/abs/2609.21133v1" }, { "catalogId": "ref-e4aa4c5754b8", "catalogTitle": "Demo of SemWeave: Semantic Common Expressions for LLM-powered Query Processing", "status": "included", "workId": "ref-e4aa4c5754b8", "source": "https://doi.org/10.1145/3788853.3801593" }, { "catalogId": "ref-0dd51ec5b206", "catalogTitle": "100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "ref-0dd51ec5b206", "source": "https://doi.org/10.1145/3802002" }, { "catalogId": "arxiv-2511-07663", "catalogTitle": "Cortex AISQL: A Production SQL Engine for Unstructured Data", "status": "included", "workId": "arxiv-2511-07663", "source": "https://arxiv.org/abs/2511.07663v3" }, { "catalogId": "arxiv-2602-01701", "catalogTitle": "Meta Engine: A Unified Semantic Query Engine on Heterogeneous LLM-Based Query Systems", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "arxiv-2602-01701", "source": "https://arxiv.org/abs/2602.01701v2" }, { "catalogId": "arxiv-2606-29151", "catalogTitle": "CADENZA: Compiling Natural-Language Intent into Task-Specific Operator DAGs for Semantic Query Processing", "status": "included", "workId": "arxiv-2606-29151", "source": "https://arxiv.org/abs/2606.29151v3" }, { "catalogId": "arxiv-2512-05399", "catalogTitle": "Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees", "status": "included", "workId": "arxiv-2512-05399", "source": "https://arxiv.org/abs/2512.05399v1" }, { "catalogId": "ref-43d0f45c6e32", "catalogTitle": "Accelerating Approximate Analytical Join Queries over Unstructured Data with Statistical Guarantees", "status": "included", "workId": "ref-43d0f45c6e32", "source": "https://doi.org/10.1145/3802004" }, { "catalogId": "arxiv-2603-17223", "catalogTitle": "ListK: Semantic ORDER BY and LIMIT K with Listwise Prompting", "status": "included", "workId": "arxiv-2603-17223", "source": "https://arxiv.org/abs/2603.17223v1" }, { "catalogId": "arxiv-2503-20119", "catalogTitle": "Approximating Opaque Top-k Queries", "status": "included", "workId": "arxiv-2503-20119", "source": "https://arxiv.org/abs/2503.20119v1" }, { "catalogId": "arxiv-2502-18470", "catalogTitle": "RankLLM: A Framework for Ranking with Large Language Models", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "arxiv-2502-18470", "source": "https://arxiv.org/abs/2505.19284v1" }, { "catalogId": "arxiv-2312-02724", "catalogTitle": "RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!", "status": "included", "workId": "arxiv-2312-02724", "source": "https://arxiv.org/abs/2312.02724v1" }, { "catalogId": "arxiv-2607-00254", "catalogTitle": "Query-Centric Optimization of AI Workflows via Approximate Query Processing and Proxy Models", "status": "included", "workId": "arxiv-2607-00254", "source": "https://arxiv.org/abs/2607.00254v2" }, { "catalogId": "arxiv-2403-14902", "catalogTitle": "Aero/Hydro: Adaptive Query Processing of ML Queries", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "arxiv-2403-14902", "source": "https://arxiv.org/abs/2403.14902v1" }, { "catalogId": "arxiv-1911-00231", "catalogTitle": "Extending Relational Query Processing with ML Inference", "status": "included", "workId": "arxiv-1911-00231", "source": "https://arxiv.org/abs/1911.00231v1" }, { "catalogId": "arxiv-2312-17355", "catalogTitle": "The Duck's Brain: Training and Inference of Neural Networks in Modern Database Engines", "status": "included", "workId": "arxiv-2312-17355", "source": "https://arxiv.org/abs/2312.17355v1" }, { "catalogId": "ref-a7c381b5e4ce", "catalogTitle": "MADlib: The MADlib Analytics Library, or MAD Skills, the SQL", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "ref-a7c381b5e4ce", "source": "https://doi.org/10.14778/2367502.2367510" }, { "catalogId": "ref-3e4a67ac6d74", "catalogTitle": "DuckDB: an Embeddable Analytical Database", "status": "included", "workId": "ref-3e4a67ac6d74", "source": "https://doi.org/10.1145/3299869.3320212" }, { "catalogId": "ref-84654a2d3434", "catalogTitle": "MonetDB/X100: Hyper-Pipelining Query Execution", "status": "included", "workId": "ref-84654a2d3434", "source": "https://www.cidrdb.org/cidr2005/papers/P19.pdf" }, { "catalogId": "ref-3dff26b27bff", "catalogTitle": "BioDEX: Large-Scale Biomedical Adverse Drug Event Extraction for Real-World Pharmacovigilance", "status": "included", "workId": "ref-3dff26b27bff", "source": "https://doi.org/10.18653/v1/2023.findings-emnlp.896" }, { "catalogId": "arxiv-2510-08489", "catalogTitle": "Implementing Semantic Join Operators Efficiently", "status": "included", "workId": "arxiv-2510-08489", "source": "https://arxiv.org/abs/2510.08489v1" }, { "catalogId": "arxiv-2505-14661", "catalogTitle": "Abacus: A Cost-Based Optimizer for Semantic Operator Systems", "status": "included", "workId": "arxiv-2505-14661", "source": "https://arxiv.org/abs/2505.14661v3" }, { "catalogId": "arxiv-2507-06515", "catalogTitle": "Quest: Query Optimization in Unstructured Document Analysis", "status": "included", "workId": "arxiv-2507-06515", "source": "https://arxiv.org/abs/2507.06515v2" }, { "catalogId": "arxiv-2509-12610", "catalogTitle": "ScaleDoc: Scaling LLM-based Predicates over Large Document Collections", "status": "included", "workId": "arxiv-2509-12610", "source": "https://arxiv.org/abs/2509.12610v2" }, { "catalogId": "arxiv-2603-04799", "catalogTitle": "Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter Paradigm", "status": "included", "workId": "arxiv-2603-04799", "source": "https://arxiv.org/abs/2603.04799v1" }, { "catalogId": "ref-21402d1d1aea", "catalogTitle": "Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees", "status": "included", "workId": "ref-21402d1d1aea", "source": "https://arxiv.org/abs/2509.02896v2" }, { "catalogId": "ref-92c7cd3291ab", "catalogTitle": "KEN: An Execution Engine for Unstructured Database Systems", "status": "included", "workId": "ref-92c7cd3291ab", "source": "https://www.vldb.org/pvldb/vol19/p902-kossmann.pdf" }, { "catalogId": "arxiv-2508-05012", "catalogTitle": "Making Prompts First-Class Citizens for Adaptive LLM Pipelines", "status": "included", "workId": "arxiv-2508-05012", "source": "https://arxiv.org/abs/2508.05012v2" }, { "catalogId": "arxiv-2604-00660", "catalogTitle": "Streaming Model Cascades for Semantic SQL", "status": "included", "workId": "arxiv-2604-00660", "source": "https://arxiv.org/abs/2604.00660v2" }, { "catalogId": "arxiv-2402-17882", "catalogTitle": "BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra", "status": "included", "workId": "arxiv-2402-17882", "source": "https://arxiv.org/abs/2402.17882v2" }, { "catalogId": "arxiv-2408-00884", "catalogTitle": "Hybrid Querying Over Relational Databases and Large Language Models", "status": "included", "workId": "arxiv-2408-00884", "source": "https://arxiv.org/abs/2408.00884v2" }, { "catalogId": "ref-efdd20df7d0b", "catalogTitle": "Logical and Physical Optimizations for SQL Query Execution over Large Language Models", "status": "included", "workId": "ref-efdd20df7d0b", "source": "https://doi.org/10.1145/3725411" }, { "catalogId": "ref-d845a48dcc81", "catalogTitle": "ThalamusDB: Approximate Query Processing on Multi-Modal Data", "status": "included", "workId": "ref-d845a48dcc81", "source": "https://api.crossref.org/works/10.1145%2F3654989" }, { "catalogId": "ref-c1f091aed610", "catalogTitle": "Approximate Selection with Guarantees using Proxies", "status": "included", "workId": "ref-c1f091aed610", "source": "https://www.vldb.org/pvldb/vol13/p1990-kang.pdf" }, { "catalogId": "ref-120601be24c4", "catalogTitle": "Accelerating Approximate Aggregation Queries with Expensive Predicates", "status": "included", "workId": "ref-120601be24c4", "source": "https://www.vldb.org/pvldb/vol14/p2341-kang.pdf" }, { "catalogId": "ref-c6cf5f1702f9", "catalogTitle": "Accelerating Machine Learning Inference with Probabilistic Predicates", "status": "included", "workId": "ref-c6cf5f1702f9", "source": "https://doi.org/10.1145/3183713.3183751" }, { "catalogId": "ref-564f2022e48d", "catalogTitle": "Wander Join: Online Aggregation for Joins", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "ref-564f2022e48d", "source": "https://doi.org/10.1145/2882903.2915235" }, { "catalogId": "ref-37c0c1fa8efa", "catalogTitle": "Eddies: Continuously Adaptive Query Processing", "status": "included", "workId": "ref-37c0c1fa8efa", "source": "https://doi.org/10.1145/342009.335420" }, { "catalogId": "ref-f7ee7814e14e", "catalogTitle": "BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics", "status": "included", "workId": "ref-f7ee7814e14e", "source": "https://arxiv.org/abs/1805.01046v2" }, { "catalogId": "ref-8891df20ddbe", "catalogTitle": "NoScope: Optimizing Neural Network Queries over Video at Scale", "status": "included", "workId": "ref-8891df20ddbe", "source": "https://www.vldb.org/pvldb/vol10/p1586-kang.pdf" }, { "catalogId": "arxiv-2409-00847", "catalogTitle": "The Design of an LLM-powered Unstructured Analytics System (Aryn/Sycamore)", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "arxiv-2409-00847", "source": "https://arxiv.org/abs/2409.00847v3" }, { "catalogId": "ref-f9e3f7194e66", "catalogTitle": "Apache DataFusion: A Fast, Extensible Query Engine for Building High-Quality Data-Centric Systems", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "ref-f9e3f7194e66", "source": "https://doi.org/10.1145/3626246.3653368" }, { "catalogId": "arxiv-2609-19491", "catalogTitle": "Efficiently Linking Unstructured Data for Multi-step Reasoning", "status": "included", "workId": "arxiv-2609-19491", "source": "https://arxiv.org/abs/2609.19491v1" }, { "catalogId": "arxiv-2609-09002", "catalogTitle": "Factorized and Vectorized Execution: Optimizing Analytical and Semantic Queries over Relations", "status": "included", "workId": "arxiv-2609-09002", "source": "https://arxiv.org/abs/2609.09002v1" }, { "catalogId": "arxiv-2309-06180", "catalogTitle": "vLLM: Efficient Memory Management for Large Language Model Serving with PagedAttention", "status": "included", "workId": "arxiv-2309-06180", "source": "https://arxiv.org/abs/2309.06180v1" }, { "catalogId": "arxiv-2312-07104", "catalogTitle": "SGLang: Efficient Execution of Structured Language Model Programs", "status": "included", "workId": "arxiv-2312-07104", "source": "https://arxiv.org/abs/2312.07104v2" }, { "catalogId": "ref-76210079970f", "catalogTitle": "Orca: A Distributed Serving System for Transformer-Based Generative Models", "status": "included", "workId": "ref-76210079970f", "source": "https://www.usenix.org/conference/osdi22/presentation/yu" }, { "catalogId": "ref-bf0630162d5d", "catalogTitle": "Sarathi-Serve: Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "ref-bf0630162d5d", "source": "https://www.usenix.org/conference/osdi24/presentation/agrawal" }, { "catalogId": "ref-d08d91468182", "catalogTitle": "DistServe: Disaggregating Prefill and Decoding for Goodput-Optimized Large Language Model Serving", "status": "included", "workId": "ref-d08d91468182", "source": "https://www.usenix.org/conference/osdi24/presentation/zhong-yinmin" }, { "catalogId": "ref-4a9db4de3b2b", "catalogTitle": "Llumnix: Dynamic Scheduling for Large Language Model Serving", "status": "included", "workId": "ref-4a9db4de3b2b", "source": "https://www.usenix.org/conference/osdi24/presentation/sun-biao" }, { "catalogId": "ref-c2e55193e68a", "catalogTitle": "Prompt Cache: Modular Attention Reuse for Low-Latency Inference", "status": "included", "workId": "ref-c2e55193e68a", "source": "https://arxiv.org/abs/2311.04934v2" }, { "catalogId": "arxiv-2512-03389", "catalogTitle": "Continuous Prompts: LLM-Augmented Pipeline Processing over Unstructured Streams", "status": "included", "workId": "arxiv-2512-03389", "source": "https://arxiv.org/abs/2512.03389v1" }, { "catalogId": "arxiv-2602-05134", "catalogTitle": "SemPipes: Optimizable Semantic Data Operators for Tabular Machine Learning Pipelines", "status": "included", "workId": "arxiv-2602-05134", "source": "https://arxiv.org/abs/2602.05134v1" }, { "catalogId": "arxiv-2601-05536", "catalogTitle": "Task Cascades for Efficient Unstructured Data Processing", "status": "included", "workId": "arxiv-2601-05536", "source": "https://arxiv.org/abs/2601.05536v1" }, { "catalogId": "arxiv-2509-02751", "catalogTitle": "Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics", "status": "included", "workId": "arxiv-2509-02751", "source": "https://arxiv.org/abs/2509.02751v1" }, { "catalogId": "arxiv-2408-14717", "catalogTitle": "Text2SQL is Not Enough: Unifying AI and Databases with TAG", "status": "included", "workId": "arxiv-2408-14717", "source": "https://arxiv.org/abs/2408.14717v1" }, { "catalogId": "arxiv-2307-07306", "catalogTitle": "C3: Zero-shot Text-to-SQL with ChatGPT", "status": "included", "workId": "arxiv-2307-07306", "source": "https://arxiv.org/abs/2307.07306v1" }, { "catalogId": "ref-c289f402557f", "catalogTitle": "In-depth Analysis of LLM-Based Schema Linking", "status": "included", "workId": "ref-c289f402557f", "source": "https://www.openproceedings.org/2026/conf/edbt/paper-24.pdf" }, { "catalogId": "arxiv-2205-09911", "catalogTitle": "Can Foundation Models Wrangle Your Data?", "status": "included", "workId": "arxiv-2205-09911", "source": "https://arxiv.org/abs/2205.09911v2" }, { "catalogId": "ref-547df79ea94f", "catalogTitle": "Booster: Leveraging Large Language Models for Enhancing Entity Resolution", "status": "included", "workId": "ref-547df79ea94f", "source": "https://arxiv.org/abs/2403.06434v1" }, { "catalogId": "ref-58178413b245", "catalogTitle": "Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching", "status": "included", "workId": "ref-58178413b245", "source": "https://arxiv.org/abs/2405.16884v3" }, { "catalogId": "ref-eded7ed7ba25", "catalogTitle": "Entity Matching Using Large Language Models", "status": "included", "workId": "ref-eded7ed7ba25", "source": "https://arxiv.org/abs/2310.11244v4" }, { "catalogId": "ref-c2f9278dc837", "catalogTitle": "Fine-Tuning Large Language Models for Entity Matching", "status": "included", "workId": "ref-c2f9278dc837", "source": "https://arxiv.org/abs/2409.08185v2" }, { "catalogId": "ref-59c3b3b8d8eb", "catalogTitle": "UniDM: A Unified Framework for Data Manipulation with Large Language Models", "status": "included", "workId": "ref-59c3b3b8d8eb", "source": "https://arxiv.org/abs/2405.06510v1" }, { "catalogId": "ref-69a564882375", "catalogTitle": "LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation", "status": "included", "workId": "ref-69a564882375", "source": "https://arxiv.org/abs/2410.21520v4" }, { "catalogId": "ref-951a1d42efbc", "catalogTitle": "Large Language Models as Data Preprocessors", "status": "included", "workId": "ref-951a1d42efbc", "source": "https://www.vldb.org/workshops/2024/proceedings/TaDA/TaDA.11.pdf" }, { "catalogId": "ref-27a51549dee0", "catalogTitle": "LLMs with User-Defined Prompts as Generic Data Operators for Reliable Data Processing / LLM-GDO", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "ref-27a51549dee0", "source": "https://arxiv.org/abs/2312.16351v1" }, { "catalogId": "ref-612428ef67d8", "catalogTitle": "Relationalizing Tables with Large Language Models: The Promise and Challenges", "status": "included", "workId": "ref-612428ef67d8", "source": "https://api.crossref.org/works/10.1109%2FICDEW61823.2024.00045" }, { "catalogId": "ref-53b225c975c0", "catalogTitle": "Table-GPT: Table Fine-Tuned GPT for Diverse Table Tasks", "status": "included", "workId": "ref-53b225c975c0", "source": "https://www.microsoft.com/en-us/research/wp-content/uploads/2024/04/Table-GPT.pdf" }, { "catalogId": "ref-c31673a03164", "catalogTitle": "SANTOS: Relationship-Based Semantic Table Union Search", "status": "included", "workId": "ref-c31673a03164", "source": "https://arxiv.org/abs/2209.13589v1" }, { "catalogId": "ref-7ef6e5010ea6", "catalogTitle": "NextiaJD: Towards Scalable Data Discovery", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "ref-7ef6e5010ea6", "source": "https://edbt2021proceedings.github.io/docs/p61.pdf" }, { "catalogId": "ref-ed864a72efea", "catalogTitle": "The Magellan Data Repository", "status": "excluded", "reason": "The primary source identifies this as a data repository, not a research paper.", "source": "https://sites.google.com/site/anhaidgroup/useful-stuff/the-magellan-data-repository" }, { "catalogId": "arxiv-2409-02038", "catalogTitle": "BEAVER: An Enterprise Benchmark for Text-to-SQL", "status": "included", "workId": "arxiv-2409-02038", "source": "https://arxiv.org/abs/2409.02038v3" }, { "catalogId": "arxiv-2504-04808", "catalogTitle": "ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines", "status": "included", "workId": "arxiv-2504-04808", "source": "https://arxiv.org/abs/2504.04808v2" }, { "catalogId": "ref-6da435766c04", "catalogTitle": "CAESURA: Language Models as Multi-Modal Query Planners", "status": "included", "workId": "ref-6da435766c04", "source": "https://arxiv.org/abs/2308.03424v1" }, { "catalogId": "arxiv-2411-07763", "catalogTitle": "Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows", "status": "included", "workId": "arxiv-2411-07763", "source": "https://arxiv.org/abs/2411.07763v2" }, { "catalogId": "arxiv-2305-03111", "catalogTitle": "BIRD: A Big Bench for Large-Scale Database Grounded Text-to-SQLs", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "arxiv-2305-03111", "source": "https://arxiv.org/abs/2305.03111v3" }, { "catalogId": "arxiv-2106-11455", "catalogTitle": "KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers", "status": "included", "workId": "arxiv-2106-11455", "source": "https://arxiv.org/abs/2106.11455v1" }, { "catalogId": "arxiv-2010-11246", "catalogTitle": "SQUALL: On the Potential of Lexico-Logical Alignments for Semantic Parsing to SQL Queries", "status": "included", "workId": "arxiv-2010-11246", "source": "https://arxiv.org/abs/2010.11246v1" }, { "catalogId": "arxiv-2509-24405", "catalogTitle": "Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language Agents", "status": "included", "workId": "arxiv-2509-24405", "source": "https://arxiv.org/abs/2509.24405v1" }, { "catalogId": "arxiv-2510-07309", "catalogTitle": "Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain / CORGI", "status": "included", "workId": "arxiv-2510-07309", "source": "https://arxiv.org/abs/2510.07309v4" }, { "catalogId": "arxiv-2511-17190", "catalogTitle": "AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale", "status": "included", "workId": "arxiv-2511-17190", "source": "https://arxiv.org/abs/2511.17190v1" }, { "catalogId": "arxiv-2502-00675", "catalogTitle": "ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration", "status": "included", "workId": "arxiv-2502-00675", "source": "https://arxiv.org/abs/2502.00675v5" }, { "catalogId": "arxiv-2511-21402", "catalogTitle": "Text-to-SQL as Dual-State Reasoning / DSR-SQL", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "arxiv-2511-21402", "source": "https://arxiv.org/abs/2511.21402v1" }, { "catalogId": "arxiv-2602-16720", "catalogTitle": "APEX-SQL: Talking to the Data via Agentic Exploration for Text-to-SQL", "status": "included", "workId": "arxiv-2602-16720", "source": "https://arxiv.org/abs/2602.16720v2" }, { "catalogId": "arxiv-2408-04667", "catalogTitle": "Non-determinism of \"Deterministic\" LLM Settings", "status": "included", "workId": "arxiv-2408-04667", "source": "https://arxiv.org/abs/2408.04667v5" }, { "catalogId": "arxiv-2210-02875", "catalogTitle": "Binding Language Models in Symbolic Languages", "status": "included", "workId": "arxiv-2210-02875", "source": "https://arxiv.org/abs/2210.02875v2" }, { "catalogId": "arxiv-2312-13264", "catalogTitle": "dIR: Discrete Information Retrieval", "status": "included", "note": "Directory uses the primary source title; catalog wording differs.", "workId": "arxiv-2312-13264", "source": "https://arxiv.org/abs/2312.13264v1" }, { "catalogId": "arxiv-2304-09433", "catalogTitle": "Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes", "status": "included", "workId": "arxiv-2304-09433", "source": "https://arxiv.org/abs/2304.09433v3" }, { "catalogId": "arxiv-2406-15652", "catalogTitle": "GenSQL: A Probabilistic Programming System for Querying Generative Models of Database Tables", "status": "included", "workId": "arxiv-2406-15652", "source": "https://arxiv.org/abs/2406.15652v1" }, { "catalogId": "semreuse", "catalogTitle": "SemReuse: Certified Reuse of Cached Natural-Language Views for Semantic Operators", "status": "included", "workId": "semreuse", "source": "https://arxiv.org/abs/2610.16035v1" }, { "catalogId": "imlane", "catalogTitle": "IMLane: Composable Framework for Efficient AI Function Execution in Database Engine", "status": "included", "workId": "imlane", "source": "https://www.vldb.org/pvldb/vol19/p4223-xu.pdf" } ], "people": [ { "id": "liana-patel", "name": "Liana Patel" }, { "id": "siddharth-jha", "name": "Siddharth Jha" }, { "id": "melissa-pan", "name": "Melissa Pan" }, { "id": "harshit-gupta", "name": "Harshit Gupta" }, { "id": "parth-asawa", "name": "Parth Asawa" }, { "id": "carlos-guestrin", "name": "Carlos Guestrin" }, { "id": "matei-zaharia", "name": "Matei Zaharia" }, { "id": "chunwei-liu", "name": "Chunwei Liu" }, { "id": "matthew-russo", "name": "Matthew Russo" }, { "id": "michael-cafarella", "name": "Michael Cafarella" }, { "id": "lei-cao", "name": "Lei Cao" }, { "id": "peter-baille-chen", "name": "Peter Baille Chen" }, { "id": "zui-chen", "name": "Zui Chen" }, { "id": "michael-franklin", "name": "Michael Franklin" }, { "id": "tim-kraska", "name": "Tim Kraska" }, { "id": "samuel-madden", "name": "Samuel Madden" }, { "id": "gerardo-vitagliano", "name": "Gerardo Vitagliano" }, { "id": "shreya-shankar", "name": "Shreya Shankar" }, { "id": "tristan-chambers", "name": "Tristan Chambers" }, { "id": "tarak-shah", "name": "Tarak Shah" }, { "id": "aditya-g-parameswaran", "name": "Aditya G. Parameswaran" }, { "id": "eugene-wu", "name": "Eugene Wu" }, { "id": "shicheng-liu", "name": "Shicheng Liu" }, { "id": "jialiang-xu", "name": "Jialiang Xu" }, { "id": "wesley-tjangnaka", "name": "Wesley Tjangnaka" }, { "id": "sina-j-semnani", "name": "Sina J. Semnani" }, { "id": "chen-jie-yu", "name": "Chen Jie Yu" }, { "id": "monica-s-lam", "name": "Monica S. Lam" }, { "id": "hanjun-dai", "name": "Hanjun Dai" }, { "id": "bethany-yixin-wang", "name": "Bethany Yixin Wang" }, { "id": "xingchen-wan", "name": "Xingchen Wan" }, { "id": "bo-dai", "name": "Bo Dai" }, { "id": "sherry-yang", "name": "Sherry Yang" }, { "id": "azade-nova", "name": "Azade Nova" }, { "id": "pengcheng-yin", "name": "Pengcheng Yin" }, { "id": "phitchaya-mangpo-phothilimthana", "name": "Phitchaya Mangpo Phothilimthana" }, { "id": "charles-sutton", "name": "Charles Sutton" }, { "id": "dale-schuurmans", "name": "Dale Schuurmans" }, { "id": "shu-liu", "name": "Shu Liu" }, { "id": "asim-biswal", "name": "Asim Biswal" }, { "id": "amog-kamsetty", "name": "Amog Kamsetty" }, { "id": "audrey-cheng", "name": "Audrey Cheng" }, { "id": "luis-gaspar-schroeder", "name": "Luis Gaspar Schroeder" }, { "id": "shiyi-cao", "name": "Shiyi Cao" }, { "id": "xiangxi-mo", "name": "Xiangxi Mo" }, { "id": "ion-stoica", "name": "Ion Stoica" }, { "id": "joseph-e-gonzalez", "name": "Joseph E. Gonzalez" }, { "id": "jiale-lao", "name": "Jiale Lao" }, { "id": "andreas-zimmerer", "name": "Andreas Zimmerer" }, { "id": "olga-ovcharenko", "name": "Olga Ovcharenko" }, { "id": "tianji-cong", "name": "Tianji Cong" }, { "id": "michael-cochez", "name": "Michael Cochez" }, { "id": "fatma-ozcan", "name": "Fatma Özcan" }, { "id": "gautam-gupta", "name": "Gautam Gupta" }, { "id": "thibaud-hottelier", "name": "Thibaud Hottelier" }, { "id": "h-v-jagadish", "name": "H. V. Jagadish" }, { "id": "kris-kissel", "name": "Kris Kissel" }, { "id": "sebastian-schelter", "name": "Sebastian Schelter" }, { "id": "andreas-kipf", "name": "Andreas Kipf" }, { "id": "immanuel-trummer", "name": "Immanuel Trummer" }, { "id": "kangkang-qi", "name": "Kangkang Qi" }, { "id": "dongyang-xie", "name": "Dongyang Xie" }, { "id": "wenbo-li", "name": "Wenbo Li" }, { "id": "hao-zhang", "name": "Hao Zhang" }, { "id": "yuanyuan-zhu", "name": "Yuanyuan Zhu" }, { "id": "jeffrey-xu-yu", "name": "Jeffrey Xu Yu" }, { "id": "kangfei-zhao", "name": "Kangfei Zhao" }, { "id": "qiyan-deng", "name": "Qiyan Deng" }, { "id": "jianhui-li", "name": "Jianhui Li" }, { "id": "chengliang-chai", "name": "Chengliang Chai" }, { "id": "jinqi-liu", "name": "Jinqi Liu" }, { "id": "junzhi-she", "name": "Junzhi She" }, { "id": "kaisen-jin", "name": "Kaisen Jin" }, { "id": "zhaoze-sun", "name": "Zhaoze Sun" }, { "id": "yuhao-deng", "name": "Yuhao Deng" }, { "id": "jia-yuan", "name": "Jia Yuan" }, { "id": "ye-yuan", "name": "Ye Yuan" }, { "id": "guoren-wang", "name": "Guoren Wang" }, { "id": "lindsey-linxi-wei", "name": "Lindsey Linxi Wei" }, { "id": "sepanta-zeighami", "name": "Sepanta Zeighami" }, { "id": "yeounoh-chung", "name": "Yeounoh Chung" }, { "id": "charles-frye", "name": "Charles Frye" }, { "id": "fergus-finn", "name": "Fergus Finn" }, { "id": "arnav-dhariya", "name": "Arnav Dhariya" }, { "id": "joseph-barrow", "name": "Joseph Barrow" }, { "id": "meryem-arik", "name": "Meryem Arik" }, { "id": "yunxiang-su", "name": "Yunxiang Su" }, { "id": "tianjing-zeng", "name": "Tianjing Zeng" }, { "id": "zhongjun-ding", "name": "Zhongjun Ding" }, { "id": "yin-lin", "name": "Yin Lin" }, { "id": "rong-zhu", "name": "Rong Zhu" }, { "id": "zhewei-wei", "name": "Zhewei Wei" }, { "id": "bolin-ding", "name": "Bolin Ding" }, { "id": "jingren-zhou", "name": "Jingren Zhou" }, { "id": "christos-tsapelas", "name": "Christos Tsapelas" }, { "id": "georgia-koutrika", "name": "Georgia Koutrika" }, { "id": "yannis-ioannidis", "name": "Yannis Ioannidis" }, { "id": "zhengle-wang", "name": "Zhengle Wang" }, { "id": "hanxu-yan", "name": "Hanxu Yan" }, { "id": "fuheng-zhao", "name": "Fuheng Zhao" }, { "id": "oktie-hassanzadeh", "name": "Oktie Hassanzadeh" }, { "id": "dharmashankar-subramanian", "name": "Dharmashankar Subramanian" }, { "id": "wenkai-dong", "name": "Wenkai Dong" }, { "id": "yifan-wang", "name": "Yifan Wang" }, { "id": "hojae-son", "name": "Hojae Son" }, { "id": "md-ashraful-islam", "name": "Md Ashraful Islam" }, { "id": "huy-gia-cao", "name": "Huy Gia Cao" }, { "id": "hui-guan", "name": "Hui Guan" }, { "id": "marco-serafini", "name": "Marco Serafini" }, { "id": "anas-dorbani", "name": "Anas Dorbani" }, { "id": "sunny-yasser", "name": "Sunny Yasser" }, { "id": "jimmy-lin", "name": "Jimmy Lin" }, { "id": "amine-mhedhbi", "name": "Amine Mhedhbi" }, { "id": "udesh-kumarasinghe", "name": "Udesh Kumarasinghe" }, { "id": "tyler-liu", "name": "Tyler Liu" }, { "id": "ahmed-r-mahmood", "name": "Ahmed R. Mahmood" }, { "id": "walid-g-aref", "name": "Walid G. Aref" }, { "id": "qiuyang-mang", "name": "Qiuyang Mang" }, { "id": "yufan-xiang", "name": "Yufan Xiang" }, { "id": "hangrui-zhou", "name": "Hangrui Zhou" }, { "id": "runyuan-he", "name": "Runyuan He" }, { "id": "jiaxiang-yu", "name": "Jiaxiang Yu" }, { "id": "hanchen-li", "name": "Hanchen Li" }, { "id": "alvin-cheung", "name": "Alvin Cheung" }, { "id": "jiayue-chen", "name": "Jiayue Chen" }, { "id": "yiming-pan", "name": "Yiming Pan" }, { "id": "tahseen-rabbani", "name": "Tahseen Rabbani" }, { "id": "sohaib", "name": "Sohaib" }, { "id": "divyakant-agrawal", "name": "Divyakant Agrawal" }, { "id": "amr-el-abbadi", "name": "Amr El Abbadi" }, { "id": "paritosh-aggarwal", "name": "Paritosh Aggarwal" }, { "id": "anupam-datta", "name": "Anupam Datta" }, { "id": "dimitris-tsirogiannis", "name": "Dimitris Tsirogiannis" }, { "id": "pawel-liskowski", "name": "Paweł Liskowski" }, { "id": "zihan-li", "name": "Zihan Li" }, { "id": "benjamin-han", "name": "Benjamin Han" }, { "id": "puxuan-yu", "name": "Puxuan Yu" }, { "id": "varich-boonsanong", "name": "Varich Boonsanong" }, { "id": "kyoungmin-kim", "name": "Kyoungmin Kim" }, { "id": "martin-catheland", "name": "Martin Catheland" }, { "id": "anastasia-ailamaki", "name": "Anastasia Ailamaki" }, { "id": "christopher-gou", "name": "Christopher Gou" }, { "id": "aditya-banerjee", "name": "Aditya Banerjee" }, { "id": "jiaxuan-wang", "name": "Jiaxuan Wang" }, { "id": "tianyang-liu", "name": "Tianyang Liu" }, { "id": "canwen-xu", "name": "Canwen Xu" }, { "id": "fangyu-lei", "name": "Fangyu Lei" }, { "id": "nikki-lijing-kuang", "name": "Nikki Lijing Kuang" }, { "id": "jixuan-chen", "name": "Jixuan Chen" }, { "id": "tao-yu", "name": "Tao Yu" }, { "id": "julian-mcauley", "name": "Julian McAuley" }, { "id": "zhewei-yao", "name": "Zhewei Yao" }, { "id": "yuxiong-he", "name": "Yuxiong He" }, { "id": "zhengren-wang", "name": "Zhengren Wang" }, { "id": "dongwen-yao", "name": "Dongwen Yao" }, { "id": "bozhou-li", "name": "Bozhou Li" }, { "id": "dongsheng-ma", "name": "Dongsheng Ma" }, { "id": "bo-li", "name": "Bo Li" }, { "id": "zhiyu-li", "name": "Zhiyu Li" }, { "id": "feiyu-xiong", "name": "Feiyu Xiong" }, { "id": "bin-cui", "name": "Bin Cui" }, { "id": "linpeng-tang", "name": "Linpeng Tang" }, { "id": "wentao-zhang", "name": "Wentao Zhang" }, { "id": "ruofan-wu", "name": "Ruofan Wu" }, { "id": "peiran-xu", "name": "Peiran Xu" }, { "id": "xiaolong-li", "name": "Xiaolong Li" }, { "id": "fan-shu", "name": "Fan Shu" }, { "id": "soyoung-yoon", "name": "Soyoung Yoon" }, { "id": "yite-wang", "name": "Yite Wang" }, { "id": "xiaodong-yu", "name": "Xiaodong Yu" }, { "id": "boyi-liu", "name": "Boyi Liu" }, { "id": "feng-yan", "name": "Feng Yan" }, { "id": "debiao-li", "name": "Debiao Li" }, { "id": "tarfah-alrashed", "name": "Tarfah Alrashed" }, { "id": "per-jacobsson", "name": "Per Jacobsson" }, { "id": "tal-neiman", "name": "Tal Neiman" }, { "id": "xianshun-chen", "name": "Xianshun Chen" }, { "id": "md-tareq-mahmood", "name": "Md. Tareq Mahmood" }, { "id": "venkatesh-emani", "name": "Venkatesh Emani" }, { "id": "hangdong-zhao", "name": "Hangdong Zhao" }, { "id": "shivaram-venkataraman", "name": "Shivaram Venkataraman" }, { "id": "rushabh-desai", "name": "Rushabh Desai" }, { "id": "jian-he", "name": "Jian He" }, { "id": "yu-xiao", "name": "Yu Xiao" }, { "id": "yves-laurent-kom-samo", "name": "Yves-Laurent Kom Samo" }, { "id": "pushkar-khadilkar", "name": "Pushkar Khadilkar" }, { "id": "sam-idicula", "name": "Sam Idicula" }, { "id": "alon-halevy", "name": "Alon Halevy" }, { "id": "yannis-papakonstantinou", "name": "Yannis Papakonstantinou" }, { "id": "bowei-chen", "name": "Bowei Chen" }, { "id": "boxin-jiang", "name": "Boxin Jiang" }, { "id": "nitish-jindal", "name": "Nitish Jindal" }, { "id": "aaron-lin", "name": "Aaron Lin" }, { "id": "kyle-schmaus", "name": "Kyle Schmaus" }, { "id": "jay-tayade", "name": "Jay Tayade" }, { "id": "weicheng-zhao", "name": "Weicheng Zhao" }, { "id": "nathan-wiegand", "name": "Nathan Wiegand" }, { "id": "ruyu-li", "name": "Ruyu Li" }, { "id": "tinghui-zhang", "name": "Tinghui Zhang" }, { "id": "haodi-ma", "name": "Haodi Ma" }, { "id": "daisy-zhe-wang", "name": "Daisy Zhe Wang" }, { "id": "jaehyun-ha", "name": "Jaehyun Ha" }, { "id": "yongjoo-park", "name": "Yongjoo Park" }, { "id": "wook-shin-han", "name": "Wook-Shin Han" }, { "id": "yuxuan-zhu", "name": "Yuxuan Zhu" }, { "id": "tengjun-jin", "name": "Tengjun Jin" }, { "id": "chenghao-mo", "name": "Chenghao Mo" }, { "id": "daniel-kang", "name": "Daniel Kang" }, { "id": "jason-shin", "name": "Jason Shin" }, { "id": "jiwon-chang", "name": "Jiwon Chang" }, { "id": "fatemeh-nargesian", "name": "Fatemeh Nargesian" }, { "id": "sahel-sharifymoghaddam", "name": "Sahel Sharifymoghaddam" }, { "id": "ronak-pradeep", "name": "Ronak Pradeep" }, { "id": "andre-slavescu", "name": "Andre Slavescu" }, { "id": "ryan-nguyen", "name": "Ryan Nguyen" }, { "id": "andrew-xu", "name": "Andrew Xu" }, { "id": "zijian-chen", "name": "Zijian Chen" }, { "id": "yilin-zhang", "name": "Yilin Zhang" }, { "id": "yidi-chen", "name": "Yidi Chen" }, { "id": "jasper-xian", "name": "Jasper Xian" }, { "id": "huayi-wang", "name": "Huayi Wang" }, { "id": "jun-xu", "name": "Jun Xu" }, { "id": "gromit-yeuk-yin-chan", "name": "Gromit Yeuk-Yin Chan" }, { "id": "gaurav-tarlok-kakkar", "name": "Gaurav Tarlok Kakkar" }, { "id": "jiashen-cao", "name": "Jiashen Cao" }, { "id": "aubhro-sengupta", "name": "Aubhro Sengupta" }, { "id": "joy-arulraj", "name": "Joy Arulraj" }, { "id": "hyesoon-kim", "name": "Hyesoon Kim" }, { "id": "konstantinos-karanasos", "name": "Konstantinos Karanasos" }, { "id": "matteo-interlandi", "name": "Matteo Interlandi" }, { "id": "doris-xin", "name": "Doris Xin" }, { "id": "fotis-psallidas", "name": "Fotis Psallidas" }, { "id": "rathijit-sen", "name": "Rathijit Sen" }, { "id": "kwanghyun-park", "name": "Kwanghyun Park" }, { "id": "ivan-popivanov", "name": "Ivan Popivanov" }, { "id": "supun-nakandal", "name": "Supun Nakandal" }, { "id": "subru-krishnan", "name": "Subru Krishnan" }, { "id": "markus-weimer", "name": "Markus Weimer" }, { "id": "yuan-yu", "name": "Yuan Yu" }, { "id": "raghu-ramakrishnan", "name": "Raghu Ramakrishnan" }, { "id": "carlo-curino", "name": "Carlo Curino" }, { "id": "maximilian-e-schule", "name": "Maximilian E. Schüle" }, { "id": "thomas-neumann", "name": "Thomas Neumann" }, { "id": "alfons-kemper", "name": "Alfons Kemper" }, { "id": "joseph-m-hellerstein", "name": "Joseph M. Hellerstein" }, { "id": "christoper-re", "name": "Christoper Ré" }, { "id": "florian-schoppmann", "name": "Florian Schoppmann" }, { "id": "eugene-fratkin", "name": "Eugene Fratkin" }, { "id": "aleksander-gorajek", "name": "Aleksander Gorajek" }, { "id": "kee-siong-ng", "name": "Kee Siong Ng" }, { "id": "caleb-welton", "name": "Caleb Welton" }, { "id": "xixuan-feng", "name": "Xixuan Feng" }, { "id": "kun-li", "name": "Kun Li" }, { "id": "arun-kumar", "name": "Arun Kumar" }, { "id": "mark-raasveldt", "name": "Mark Raasveldt" }, { "id": "hannes-muhleisen", "name": "Hannes Mühleisen" }, { "id": "peter-boncz", "name": "Peter Boncz" }, { "id": "marcin-zukowski", "name": "Marcin Zukowski" }, { "id": "niels-nes", "name": "Niels Nes" }, { "id": "karel-doosterlinck", "name": "Karel D’Oosterlinck" }, { "id": "francois-remy", "name": "François Remy" }, { "id": "johannes-deleu", "name": "Johannes Deleu" }, { "id": "thomas-demeester", "name": "Thomas Demeester" }, { "id": "chris-develder", "name": "Chris Develder" }, { "id": "klim-zaporojets", "name": "Klim Zaporojets" }, { "id": "aneiss-ghodsi", "name": "Aneiss Ghodsi" }, { "id": "simon-ellershaw", "name": "Simon Ellershaw" }, { "id": "jack-collins", "name": "Jack Collins" }, { "id": "christopher-potts", "name": "Christopher Potts" }, { "id": "sivaprasad-sudhir", "name": "Sivaprasad Sudhir" }, { "id": "xinyu-guo", "name": "Xinyu Guo" }, { "id": "han-han", "name": "Han Han" }, { "id": "hengrui-zhang", "name": "Hengrui Zhang" }, { "id": "yulong-hui", "name": "Yulong Hui" }, { "id": "yihao-liu", "name": "Yihao Liu" }, { "id": "huanchen-zhang", "name": "Huanchen Zhang" }, { "id": "nan-hou", "name": "Nan Hou" }, { "id": "jiadong-xie", "name": "Jiadong Xie" }, { "id": "ferdi-kossmann", "name": "Ferdi Kossmann" }, { "id": "ziniu-wu", "name": "Ziniu Wu" }, { "id": "alex-turk", "name": "Alex Turk" }, { "id": "nesime-tatbul", "name": "Nesime Tatbul" }, { "id": "ugur-cetintemel", "name": "Ugur Cetintemel" }, { "id": "shu-chen", "name": "Shu Chen" }, { "id": "alexander-w-lee", "name": "Alexander W. Lee" }, { "id": "deepti-raghavan", "name": "Deepti Raghavan" }, { "id": "duo-lu", "name": "Duo Lu" }, { "id": "andrew-crotty", "name": "Andrew Crotty" }, { "id": "parker-glenn", "name": "Parker Glenn" }, { "id": "parag-pravin-dakle", "name": "Parag Pravin Dakle" }, { "id": "liang-wang", "name": "Liang Wang" }, { "id": "preethi-raghavan", "name": "Preethi Raghavan" }, { "id": "dario-satriani", "name": "Dario Satriani" }, { "id": "enzo-veltri", "name": "Enzo Veltri" }, { "id": "donatello-santoro", "name": "Donatello Santoro" }, { "id": "sara-rosato", "name": "Sara Rosato" }, { "id": "simone-varriale", "name": "Simone Varriale" }, { "id": "paolo-papotti", "name": "Paolo Papotti" }, { "id": "saehan-jo", "name": "Saehan Jo" }, { "id": "edward-gan", "name": "Edward Gan" }, { "id": "peter-bailis", "name": "Peter Bailis" }, { "id": "tatsunori-hashimoto", "name": "Tatsunori Hashimoto" }, { "id": "john-guibas", "name": "John Guibas" }, { "id": "yi-sun", "name": "Yi Sun" }, { "id": "yao-lu", "name": "Yao Lu" }, { "id": "aakanksha-chowdhery", "name": "Aakanksha Chowdhery" }, { "id": "srikanth-kandula", "name": "Srikanth Kandula" }, { "id": "surajit-chaudhuri", "name": "Surajit Chaudhuri" }, { "id": "feifei-li", "name": "Feifei Li" }, { "id": "bin-wu", "name": "Bin Wu" }, { "id": "ke-yi", "name": "Ke Yi" }, { "id": "zhuoyue-zhao", "name": "Zhuoyue Zhao" }, { "id": "ron-avnur", "name": "Ron Avnur" }, { "id": "john-emmons", "name": "John Emmons" }, { "id": "firas-abuzaid", "name": "Firas Abuzaid" }, { "id": "eric-anderson", "name": "Eric Anderson" }, { "id": "jonathan-fritz", "name": "Jonathan Fritz" }, { "id": "austin-lee", "name": "Austin Lee" }, { "id": "bohou-li", "name": "Bohou Li" }, { "id": "mark-lindblad", "name": "Mark Lindblad" }, { "id": "henry-lindeman", "name": "Henry Lindeman" }, { "id": "alex-meyer", "name": "Alex Meyer" }, { "id": "parth-parmar", "name": "Parth Parmar" }, { "id": "tanvi-ranade", "name": "Tanvi Ranade" }, { "id": "mehul-a-shah", "name": "Mehul A. Shah" }, { "id": "benjamin-sowell", "name": "Benjamin Sowell" }, { "id": "dan-tecuci", "name": "Dan Tecuci" }, { "id": "vinayak-thapliyal", "name": "Vinayak Thapliyal" }, { "id": "matt-welsh", "name": "Matt Welsh" }, { "id": "andrew-lamb", "name": "Andrew Lamb" }, { "id": "yijie-shen", "name": "Yijie Shen" }, { "id": "daniel-heres", "name": "Daniël Heres" }, { "id": "jayjeet-chakraborty", "name": "Jayjeet Chakraborty" }, { "id": "mehmet-ozan-kabak", "name": "Mehmet Ozan Kabak" }, { "id": "liang-chi-hsieh", "name": "Liang-Chi Hsieh" }, { "id": "chao-sun", "name": "Chao Sun" }, { "id": "jiaming-liang", "name": "Jiaming Liang" }, { "id": "haydn-jones", "name": "Haydn Jones" }, { "id": "jacob-r-gardner", "name": "Jacob R. Gardner" }, { "id": "mark-yatskar", "name": "Mark Yatskar" }, { "id": "zachary-ives", "name": "Zachary Ives" }, { "id": "woosuk-kwon", "name": "Woosuk Kwon" }, { "id": "zhuohan-li", "name": "Zhuohan Li" }, { "id": "siyuan-zhuang", "name": "Siyuan Zhuang" }, { "id": "ying-sheng", "name": "Ying Sheng" }, { "id": "lianmin-zheng", "name": "Lianmin Zheng" }, { "id": "cody-hao-yu", "name": "Cody Hao Yu" }, { "id": "liangsheng-yin", "name": "Liangsheng Yin" }, { "id": "zhiqiang-xie", "name": "Zhiqiang Xie" }, { "id": "chuyue-sun", "name": "Chuyue Sun" }, { "id": "jeff-huang", "name": "Jeff Huang" }, { "id": "christos-kozyrakis", "name": "Christos Kozyrakis" }, { "id": "clark-barrett", "name": "Clark Barrett" }, { "id": "gyeong-in-yu", "name": "Gyeong-In Yu" }, { "id": "joo-seong-jeong", "name": "Joo Seong Jeong" }, { "id": "geon-woo-kim", "name": "Geon-Woo Kim" }, { "id": "soojeong-kim", "name": "Soojeong Kim" }, { "id": "byung-gon-chun", "name": "Byung-Gon Chun" }, { "id": "amey-agrawal", "name": "Amey Agrawal" }, { "id": "nitin-kedia", "name": "Nitin Kedia" }, { "id": "ashish-panwar", "name": "Ashish Panwar" }, { "id": "jayashree-mohan", "name": "Jayashree Mohan" }, { "id": "nipun-kwatra", "name": "Nipun Kwatra" }, { "id": "bhargav-gulavani", "name": "Bhargav Gulavani" }, { "id": "alexey-tumanov", "name": "Alexey Tumanov" }, { "id": "ramachandran-ramjee", "name": "Ramachandran Ramjee" }, { "id": "yinmin-zhong", "name": "Yinmin Zhong" }, { "id": "shengyu-liu", "name": "Shengyu Liu" }, { "id": "junda-chen", "name": "Junda Chen" }, { "id": "jianbo-hu", "name": "Jianbo Hu" }, { "id": "yibo-zhu", "name": "Yibo Zhu" }, { "id": "xuanzhe-liu", "name": "Xuanzhe Liu" }, { "id": "xin-jin", "name": "Xin Jin" }, { "id": "hao-zhang-ucsd", "name": "Hao Zhang", "identityNote": "UC San Diego; distinct from the Sema author at CUHK." }, { "id": "biao-sun", "name": "Biao Sun" }, { "id": "ziming-huang", "name": "Ziming Huang" }, { "id": "hanyu-zhao", "name": "Hanyu Zhao" }, { "id": "wencong-xiao", "name": "Wencong Xiao" }, { "id": "xinyi-zhang", "name": "Xinyi Zhang" }, { "id": "yong-li", "name": "Yong Li" }, { "id": "wei-lin", "name": "Wei Lin" }, { "id": "in-gim", "name": "In Gim" }, { "id": "guojun-chen", "name": "Guojun Chen" }, { "id": "seung-seob-lee", "name": "Seung-seob Lee" }, { "id": "nikhil-sarda", "name": "Nikhil Sarda" }, { "id": "anurag-khandelwal", "name": "Anurag Khandelwal" }, { "id": "lin-zhong", "name": "Lin Zhong" }, { "id": "matthias-boehm", "name": "Matthias Boehm" }, { "id": "siddarth-jha", "name": "Siddarth Jha" }, { "id": "xuemei-dong", "name": "Xuemei Dong" }, { "id": "chao-zhang", "name": "Chao Zhang" }, { "id": "yuhang-ge", "name": "Yuhang Ge" }, { "id": "yuren-mao", "name": "Yuren Mao" }, { "id": "yunjun-gao", "name": "Yunjun Gao" }, { "id": "lu-chen", "name": "lu Chen" }, { "id": "jinshu-lin", "name": "Jinshu Lin" }, { "id": "dongfang-lou", "name": "Dongfang Lou" }, { "id": "george-katsogiannis-meimarakis", "name": "George Katsogiannis-Meimarakis" }, { "id": "katsiaryna-mirylenka", "name": "Katsiaryna Mirylenka" }, { "id": "paolo-scotton", "name": "Paolo Scotton" }, { "id": "francesco-fusco", "name": "Francesco Fusco" }, { "id": "abdel-labbi", "name": "Abdel Labbi" }, { "id": "avanika-narayan", "name": "Avanika Narayan" }, { "id": "ines-chami", "name": "Ines Chami" }, { "id": "laurel-orr", "name": "Laurel Orr" }, { "id": "simran-arora", "name": "Simran Arora" }, { "id": "christopher-re", "name": "Christopher Ré" }, { "id": "huahang-li", "name": "Huahang Li" }, { "id": "shuangyin-li", "name": "Shuangyin Li" }, { "id": "fei-hao", "name": "Fei Hao" }, { "id": "chen-jason-zhang", "name": "Chen Jason Zhang" }, { "id": "yuanfeng-song", "name": "Yuanfeng Song" }, { "id": "lei-chen", "name": "Lei Chen" }, { "id": "tianshu-wang", "name": "Tianshu Wang" }, { "id": "xiaoyang-chen", "name": "Xiaoyang Chen" }, { "id": "hongyu-lin", "name": "Hongyu Lin" }, { "id": "xuanang-chen", "name": "Xuanang Chen" }, { "id": "xianpei-han", "name": "Xianpei Han" }, { "id": "hao-wang", "name": "Hao Wang" }, { "id": "zhenyu-zeng", "name": "Zhenyu Zeng" }, { "id": "le-sun", "name": "Le Sun" }, { "id": "ralph-peeters", "name": "Ralph Peeters" }, { "id": "aaron-steiner", "name": "Aaron Steiner" }, { "id": "christian-bizer", "name": "Christian Bizer" }, { "id": "yichen-qian", "name": "Yichen Qian" }, { "id": "yongyi-he", "name": "Yongyi He" }, { "id": "jintao-huang", "name": "Jintao Huang" }, { "id": "zhijian-ma", "name": "Zhijian Ma" }, { "id": "haibin-wang", "name": "Haibin Wang" }, { "id": "yaohua-wang", "name": "Yaohua Wang" }, { "id": "xiuyu-sun", "name": "Xiuyu Sun" }, { "id": "defu-lian", "name": "Defu Lian" }, { "id": "xinrui-he", "name": "Xinrui He" }, { "id": "yikun-ban", "name": "Yikun Ban" }, { "id": "jiaru-zou", "name": "Jiaru Zou" }, { "id": "tianxin-wei", "name": "Tianxin Wei" }, { "id": "curtiss-b-cook", "name": "Curtiss B. Cook" }, { "id": "jingrui-he", "name": "Jingrui He" }, { "id": "haochen-zhang", "name": "Haochen Zhang" }, { "id": "yuyang-dong", "name": "Yuyang Dong" }, { "id": "chuan-xiao", "name": "Chuan Xiao" }, { "id": "masafumi-oyamada", "name": "Masafumi Oyamada" }, { "id": "luyi-ma", "name": "Luyi Ma" }, { "id": "nikhil-thakurdesai", "name": "Nikhil Thakurdesai" }, { "id": "jiao-chen", "name": "Jiao Chen" }, { "id": "jianpeng-xu", "name": "Jianpeng Xu" }, { "id": "evren-korpeoglu", "name": "Evren Korpeoglu" }, { "id": "sushant-kumar", "name": "Sushant Kumar" }, { "id": "kannan-achan", "name": "Kannan Achan" }, { "id": "zezhou-huang", "name": "Zezhou Huang" }, { "id": "peng-li", "name": "Peng Li" }, { "id": "yeye-he", "name": "Yeye He" }, { "id": "dror-yashar", "name": "Dror Yashar" }, { "id": "weiwei-cui", "name": "Weiwei Cui" }, { "id": "song-ge", "name": "Song Ge" }, { "id": "haidong-zhang", "name": "Haidong Zhang" }, { "id": "danielle-rifinski-fainman", "name": "Danielle Rifinski Fainman" }, { "id": "dongmei-zhang", "name": "Dongmei Zhang" }, { "id": "aamod-khatiwada", "name": "Aamod Khatiwada" }, { "id": "grace-fan", "name": "Grace Fan" }, { "id": "roee-shraga", "name": "Roee Shraga" }, { "id": "zixuan-chen", "name": "Zixuan Chen" }, { "id": "wolfgang-gatterbauer", "name": "Wolfgang Gatterbauer" }, { "id": "renee-j-miller", "name": "Renée J. Miller" }, { "id": "mirek-riedewald", "name": "Mirek Riedewald" }, { "id": "javier-flores", "name": "Javier Flores" }, { "id": "sergi-nadal", "name": "Sergi Nadal" }, { "id": "oscar-romero", "name": "Oscar Romero" }, { "id": "peter-baile-chen", "name": "Peter Baile Chen" }, { "id": "devin-yang", "name": "Devin Yang" }, { "id": "weiyue-li", "name": "Weiyue Li" }, { "id": "fabian-wenz", "name": "Fabian Wenz" }, { "id": "yi-zhang", "name": "Yi Zhang" }, { "id": "cagatay-demiralp", "name": "Çağatay Demiralp" }, { "id": "michael-stonebraker", "name": "Michael Stonebraker" }, { "id": "matthias-urban", "name": "Matthias Urban" }, { "id": "carsten-binnig", "name": "Carsten Binnig" }, { "id": "yuxiao-ye", "name": "Yuxiao Ye" }, { "id": "ruisheng-cao", "name": "Ruisheng Cao" }, { "id": "dongchan-shin", "name": "Dongchan Shin" }, { "id": "hongjin-su", "name": "Hongjin Su" }, { "id": "zhaoqing-suo", "name": "Zhaoqing Suo" }, { "id": "hongcheng-gao", "name": "Hongcheng Gao" }, { "id": "wenjing-hu", "name": "Wenjing Hu" }, { "id": "victor-zhong", "name": "Victor Zhong" }, { "id": "caiming-xiong", "name": "Caiming Xiong" }, { "id": "ruoxi-sun", "name": "Ruoxi Sun" }, { "id": "qian-liu", "name": "Qian Liu" }, { "id": "sida-wang", "name": "Sida Wang" }, { "id": "jinyang-li", "name": "Jinyang Li" }, { "id": "binyuan-hui", "name": "Binyuan Hui" }, { "id": "ge-qu", "name": "Ge Qu" }, { "id": "jiaxi-yang", "name": "Jiaxi Yang" }, { "id": "binhua-li", "name": "Binhua Li" }, { "id": "bowen-li", "name": "Bowen Li" }, { "id": "bailin-wang", "name": "Bailin Wang" }, { "id": "bowen-qin", "name": "Bowen Qin" }, { "id": "rongyu-cao", "name": "Rongyu Cao" }, { "id": "ruiying-geng", "name": "Ruiying Geng" }, { "id": "nan-huo", "name": "Nan Huo" }, { "id": "xuanhe-zhou", "name": "Xuanhe Zhou" }, { "id": "chenhao-ma", "name": "Chenhao Ma" }, { "id": "guoliang-li", "name": "Guoliang Li" }, { "id": "kevin-c-c-chang", "name": "Kevin C. C. Chang" }, { "id": "fei-huang", "name": "Fei Huang" }, { "id": "reynold-cheng", "name": "Reynold Cheng" }, { "id": "yongbin-li", "name": "Yongbin Li" }, { "id": "chia-hsuan-lee", "name": "Chia-Hsuan Lee" }, { "id": "oleksandr-polozov", "name": "Oleksandr Polozov" }, { "id": "matthew-richardson", "name": "Matthew Richardson" }, { "id": "tianze-shi", "name": "Tianze Shi" }, { "id": "chen-zhao", "name": "Chen Zhao" }, { "id": "jordan-boyd-graber", "name": "Jordan Boyd-Graber" }, { "id": "hal-daume-iii", "name": "Hal Daumé III" }, { "id": "lillian-lee", "name": "Lillian Lee" }, { "id": "khanh-trinh-pham", "name": "Khanh Trinh Pham" }, { "id": "thu-huong-nguyen", "name": "Thu Huong Nguyen" }, { "id": "jun-jo", "name": "Jun Jo" }, { "id": "quoc-viet-hung-nguyen", "name": "Quoc Viet Hung Nguyen" }, { "id": "thanh-tam-nguyen", "name": "Thanh Tam Nguyen" }, { "id": "yue-li", "name": "Yue Li" }, { "id": "ran-tao", "name": "Ran Tao" }, { "id": "derek-hommel", "name": "Derek Hommel" }, { "id": "yusuf-denizay-donder", "name": "Yusuf Denizay Dönder" }, { "id": "sungyong-chang", "name": "Sungyong Chang" }, { "id": "david-mimno", "name": "David Mimno" }, { "id": "unso-eun-seo-jo", "name": "Unso Eun Seo Jo" }, { "id": "ziyang-wang", "name": "Ziyang Wang" }, { "id": "yuanlei-zheng", "name": "Yuanlei Zheng" }, { "id": "zhenbiao-cao", "name": "Zhenbiao Cao" }, { "id": "xiaojin-zhang", "name": "Xiaojin Zhang" }, { "id": "zhongyu-wei", "name": "Zhongyu Wei" }, { "id": "pei-fu", "name": "Pei Fu" }, { "id": "zhenbo-luo", "name": "Zhenbo Luo" }, { "id": "wei-chen", "name": "Wei Chen" }, { "id": "xiang-bai", "name": "Xiang Bai" }, { "id": "minghang-deng", "name": "Minghang Deng" }, { "id": "ashwin-ramachandran", "name": "Ashwin Ramachandran" }, { "id": "lanxiang-hu", "name": "Lanxiang Hu" }, { "id": "zhifeng-hao", "name": "Zhifeng Hao" }, { "id": "qibin-song", "name": "Qibin Song" }, { "id": "ruichu-cai", "name": "Ruichu Cai" }, { "id": "boyan-xu", "name": "Boyan Xu" }, { "id": "bowen-cao", "name": "Bowen Cao" }, { "id": "weibin-liao", "name": "Weibin Liao" }, { "id": "yushi-sun", "name": "Yushi Sun" }, { "id": "dong-fang", "name": "Dong Fang" }, { "id": "haitao-li", "name": "Haitao Li" }, { "id": "wai-lam", "name": "Wai Lam" }, { "id": "berk-atil", "name": "Berk Atil" }, { "id": "sarp-aykent", "name": "Sarp Aykent" }, { "id": "alexa-chittams", "name": "Alexa Chittams" }, { "id": "lisheng-fu", "name": "Lisheng Fu" }, { "id": "rebecca-j-passonneau", "name": "Rebecca J. Passonneau" }, { "id": "evan-radcliffe", "name": "Evan Radcliffe" }, { "id": "guru-rajan-rajagopal", "name": "Guru Rajan Rajagopal" }, { "id": "adam-sloan", "name": "Adam Sloan" }, { "id": "tomasz-tudrej", "name": "Tomasz Tudrej" }, { "id": "ferhan-ture", "name": "Ferhan Ture" }, { "id": "zhe-wu", "name": "Zhe Wu" }, { "id": "lixinyu-xu", "name": "Lixinyu Xu" }, { "id": "breck-baldwin", "name": "Breck Baldwin" }, { "id": "zhoujun-cheng", "name": "Zhoujun Cheng" }, { "id": "tianbao-xie", "name": "Tianbao Xie" }, { "id": "peng-shi", "name": "Peng Shi" }, { "id": "chengzu-li", "name": "Chengzu Li" }, { "id": "rahul-nadkarni", "name": "Rahul Nadkarni" }, { "id": "yushi-hu", "name": "Yushi Hu" }, { "id": "dragomir-radev", "name": "Dragomir Radev" }, { "id": "mari-ostendorf", "name": "Mari Ostendorf" }, { "id": "luke-zettlemoyer", "name": "Luke Zettlemoyer" }, { "id": "noah-a-smith", "name": "Noah A. Smith" }, { "id": "pablo-m-rodriguez-bertorello", "name": "Pablo M. Rodriguez Bertorello" }, { "id": "jean-rodmond-junior-laguerre", "name": "Jean Rodmond Junior Laguerre" }, { "id": "brandon-yang", "name": "Brandon Yang" }, { "id": "sabri-eyuboglu", "name": "Sabri Eyuboglu" }, { "id": "andrew-hojel", "name": "Andrew Hojel" }, { "id": "mathieu-huot", "name": "Mathieu Huot" }, { "id": "matin-ghavami", "name": "Matin Ghavami" }, { "id": "alexander-k-lew", "name": "Alexander K. Lew" }, { "id": "ulrich-schaechtle", "name": "Ulrich Schaechtle" }, { "id": "cameron-e-freer", "name": "Cameron E. Freer" }, { "id": "zane-shelby", "name": "Zane Shelby" }, { "id": "martin-c-rinard", "name": "Martin C. Rinard" }, { "id": "feras-a-saad", "name": "Feras A. Saad" }, { "id": "vikash-k-mansinghka", "name": "Vikash K. Mansinghka" }, { "id": "phat-t-tran-truong", "name": "Phat T. Tran-Truong" }, { "id": "tung-kieu", "name": "Tung Kieu" }, { "id": "xuan-bach-le", "name": "Xuan-Bach Le" }, { "id": "son-x-ha", "name": "Son X. Ha" }, { "id": "duc-kieu", "name": "Duc Kieu" }, { "id": "bin-yang", "name": "Bin Yang" }, { "id": "christian-s-jensen", "name": "Christian S. Jensen" }, { "id": "chenyang-zhang", "name": "Chenyang Zhang" }, { "id": "linjun-lu", "name": "Linjun Lu" }, { "id": "qingfeng-pan", "name": "Qingfeng Pan" }, { "id": "chen-xu", "name": "Chen Xu" }, { "id": "xianzhong-cao", "name": "Xianzhong Cao" }, { "id": "quanqing-xu", "name": "Quanqing Xu" }, { "id": "chuanhui-yang", "name": "Chuanhui Yang" } ], "works": [ { "id": "lotus", "catalogIds": ["lotus"], "title": "Semantic Operators: A Declarative Model for Rich, AI-based Data Processing", "kind": "paper", "scope": "core", "date": "2024-07-16", "topic": "Semantic operators", "url": "https://arxiv.org/abs/2407.11418v3", "metadataSource": "https://arxiv.org/abs/2407.11418", "checkedDate": "2026-10-25", "authors": [ { "name": "Liana Patel", "affiliations": ["Stanford University"], "personId": "liana-patel" }, { "name": "Siddharth Jha", "affiliations": ["UC Berkeley"], "personId": "siddharth-jha" }, { "name": "Melissa Pan", "affiliations": ["UC Berkeley"], "personId": "melissa-pan" }, { "name": "Harshit Gupta", "affiliations": ["Stanford University"], "personId": "harshit-gupta" }, { "name": "Parth Asawa", "affiliations": ["UC Berkeley"], "personId": "parth-asawa" }, { "name": "Carlos Guestrin", "affiliations": ["Stanford University"], "personId": "carlos-guestrin" }, { "name": "Matei Zaharia", "affiliations": ["UC Berkeley"], "personId": "matei-zaharia" } ], "affiliationSource": "https://arxiv.org/html/2407.11418v3" }, { "id": "uqe", "catalogIds": ["uqe"], "title": "UQE: A Query Engine for Unstructured Databases", "kind": "paper", "scope": "core", "date": "2024-06-23", "topic": "Multimodal analytics", "url": "https://arxiv.org/abs/2407.09522v2", "metadataSource": "https://arxiv.org/abs/2407.09522", "checkedDate": "2026-10-25", "authors": [ { "name": "Hanjun Dai", "affiliations": ["Google"], "personId": "hanjun-dai" }, { "name": "Bethany Yixin Wang", "affiliations": ["Google"], "personId": "bethany-yixin-wang" }, { "name": "Xingchen Wan", "affiliations": ["Google"], "personId": "xingchen-wan" }, { "name": "Bo Dai", "affiliations": ["Google", "Georgia Institute of Technology"], "personId": "bo-dai" }, { "name": "Sherry Yang", "affiliations": ["Google"], "personId": "sherry-yang" }, { "name": "Azade Nova", "affiliations": ["Google"], "personId": "azade-nova" }, { "name": "Pengcheng Yin", "affiliations": ["Google"], "personId": "pengcheng-yin" }, { "name": "Phitchaya Mangpo Phothilimthana", "affiliations": ["Google"], "personId": "phitchaya-mangpo-phothilimthana" }, { "name": "Charles Sutton", "affiliations": ["Google"], "personId": "charles-sutton" }, { "name": "Dale Schuurmans", "affiliations": ["Google", "University of Alberta"], "personId": "dale-schuurmans" } ], "affiliationSource": "https://arxiv.org/pdf/2407.09522v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "palimpzest", "catalogIds": ["palimpzest"], "title": "A Declarative System for Optimizing AI Workloads", "kind": "paper", "scope": "core", "date": "2024-05-23", "topic": "Query optimization", "url": "https://arxiv.org/abs/2405.14696v2", "metadataSource": "https://arxiv.org/abs/2405.14696", "checkedDate": "2026-10-25", "authors": [ { "name": "Chunwei Liu", "affiliations": ["MIT"], "personId": "chunwei-liu" }, { "name": "Matthew Russo", "affiliations": ["MIT"], "personId": "matthew-russo" }, { "name": "Michael Cafarella", "affiliations": ["MIT"], "personId": "michael-cafarella" }, { "name": "Lei Cao", "affiliations": ["University of Arizona"], "personId": "lei-cao" }, { "name": "Peter Baille Chen", "affiliations": ["MIT"], "personId": "peter-baille-chen" }, { "name": "Zui Chen", "affiliations": ["MIT"], "personId": "zui-chen" }, { "name": "Michael Franklin", "affiliations": ["University of Chicago"], "personId": "michael-franklin" }, { "name": "Tim Kraska", "affiliations": ["MIT"], "personId": "tim-kraska" }, { "name": "Samuel Madden", "affiliations": ["MIT"], "personId": "samuel-madden" }, { "name": "Gerardo Vitagliano", "affiliations": ["MIT"], "personId": "gerardo-vitagliano" } ], "affiliationSource": "https://arxiv.org/html/2405.14696v2" }, { "id": "docetl", "catalogIds": ["docetl"], "title": "DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing", "kind": "paper", "scope": "core", "date": "2024-10-16", "topic": "Document processing", "url": "https://arxiv.org/abs/2410.12189v3", "metadataSource": "https://arxiv.org/abs/2410.12189", "checkedDate": "2026-10-25", "authors": [ { "name": "Shreya Shankar", "affiliations": ["UC Berkeley"], "personId": "shreya-shankar" }, { "name": "Tristan Chambers", "affiliations": ["BIDS Police Records Access Project"], "personId": "tristan-chambers" }, { "name": "Tarak Shah", "affiliations": ["BIDS Police Records Access Project"], "personId": "tarak-shah" }, { "name": "Aditya G. Parameswaran", "affiliations": ["UC Berkeley"], "personId": "aditya-g-parameswaran" }, { "name": "Eugene Wu", "affiliations": ["Columbia University"], "personId": "eugene-wu" } ], "affiliationSource": "https://arxiv.org/html/2410.12189v3" }, { "id": "suql", "catalogIds": ["suql"], "title": "SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models", "kind": "paper", "scope": "core", "date": "2023-11-16", "topic": "Hybrid query languages", "url": "https://arxiv.org/abs/2311.09818v2", "metadataSource": "https://arxiv.org/abs/2311.09818", "checkedDate": "2026-10-25", "authors": [ { "name": "Shicheng Liu", "affiliations": ["Stanford University"], "personId": "shicheng-liu" }, { "name": "Jialiang Xu", "affiliations": ["Stanford University"], "personId": "jialiang-xu" }, { "name": "Wesley Tjangnaka", "affiliations": ["Stanford University"], "personId": "wesley-tjangnaka" }, { "name": "Sina J. Semnani", "affiliations": ["Stanford University"], "personId": "sina-j-semnani" }, { "name": "Chen Jie Yu", "affiliations": ["Stanford University"], "personId": "chen-jie-yu" }, { "name": "Monica S. Lam", "affiliations": ["Stanford University"], "personId": "monica-s-lam" } ], "affiliationSource": "https://arxiv.org/html/2311.09818v2" }, { "id": "sembench", "catalogIds": ["sembench"], "title": "SemBench: A Benchmark for Semantic Query Processing Engines", "kind": "paper", "scope": "core", "date": "2025-11-03", "topic": "Evaluation", "url": "https://arxiv.org/abs/2511.01716v2", "metadataSource": "https://arxiv.org/abs/2511.01716", "checkedDate": "2026-10-25", "authors": [ { "name": "Jiale Lao", "affiliations": ["Cornell University"], "personId": "jiale-lao" }, { "name": "Andreas Zimmerer", "affiliations": ["University of Technology Nuremberg"], "personId": "andreas-zimmerer" }, { "name": "Olga Ovcharenko", "affiliations": ["BIFOLD & TU Berlin"], "personId": "olga-ovcharenko" }, { "name": "Tianji Cong", "affiliations": ["University of Michigan"], "personId": "tianji-cong" }, { "name": "Matthew Russo", "affiliations": ["MIT"], "personId": "matthew-russo" }, { "name": "Gerardo Vitagliano", "affiliations": ["MIT"], "personId": "gerardo-vitagliano" }, { "name": "Michael Cochez", "affiliations": ["Vrije Universiteit Amsterdam"], "personId": "michael-cochez" }, { "name": "Fatma Özcan", "affiliations": ["Google"], "personId": "fatma-ozcan" }, { "name": "Gautam Gupta", "affiliations": ["Google"], "personId": "gautam-gupta" }, { "name": "Thibaud Hottelier", "affiliations": ["Google"], "personId": "thibaud-hottelier" }, { "name": "H. V. Jagadish", "affiliations": ["University of Michigan"], "personId": "h-v-jagadish" }, { "name": "Kris Kissel", "affiliations": ["Google"], "personId": "kris-kissel" }, { "name": "Sebastian Schelter", "affiliations": ["BIFOLD & TU Berlin"], "personId": "sebastian-schelter" }, { "name": "Andreas Kipf", "affiliations": ["University of Technology Nuremberg"], "personId": "andreas-kipf" }, { "name": "Immanuel Trummer", "affiliations": ["Cornell University"], "personId": "immanuel-trummer" } ], "affiliationSource": "https://arxiv.org/html/2511.01716v2" }, { "id": "lrobench", "catalogIds": ["lrobench"], "title": "Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis", "kind": "paper", "scope": "core", "date": "2026-03-03", "topic": "Benchmark", "url": "https://arxiv.org/abs/2603.02537v2", "metadataSource": "https://arxiv.org/abs/2603.02537", "checkedDate": "2026-10-25", "authors": [ { "name": "Yunxiang Su", "affiliations": ["Alibaba Group", "Tsinghua University"], "personId": "yunxiang-su" }, { "name": "Tianjing Zeng", "affiliations": ["Alibaba Group", "Renmin University of China"], "personId": "tianjing-zeng" }, { "name": "Zhongjun Ding", "affiliations": ["Alibaba Group"], "personId": "zhongjun-ding" }, { "name": "Yin Lin", "affiliations": ["Alibaba Group"], "personId": "yin-lin" }, { "name": "Rong Zhu", "affiliations": ["Alibaba Group"], "personId": "rong-zhu" }, { "name": "Zhewei Wei", "affiliations": ["Renmin University of China"], "personId": "zhewei-wei" }, { "name": "Bolin Ding", "affiliations": ["Alibaba Group"], "personId": "bolin-ding" }, { "name": "Jingren Zhou", "affiliations": ["Alibaba Group"], "personId": "jingren-zhou" } ], "affiliationSource": "https://arxiv.org/html/2603.02537v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "sema", "catalogIds": ["sema"], "title": "Sema: A High-performance System for LLM-based Semantic Query Processing", "kind": "paper", "scope": "core", "date": "2026-03-12", "topic": "Query optimization", "url": "https://arxiv.org/abs/2603.11622v1", "metadataSource": "https://arxiv.org/abs/2603.11622", "checkedDate": "2026-10-25", "authors": [ { "name": "Kangkang Qi", "affiliations": ["Beijing Institute of Technology"], "personId": "kangkang-qi" }, { "name": "Dongyang Xie", "affiliations": ["Wuhan University"], "personId": "dongyang-xie" }, { "name": "Wenbo Li", "affiliations": ["Wuhan University"], "personId": "wenbo-li" }, { "name": "Hao Zhang", "affiliations": ["The Chinese University of Hong Kong"], "personId": "hao-zhang" }, { "name": "Yuanyuan Zhu", "affiliations": ["Wuhan University"], "personId": "yuanyuan-zhu" }, { "name": "Jeffrey Xu Yu", "affiliations": ["HKUST (Guangzhou)"], "personId": "jeffrey-xu-yu" }, { "name": "Kangfei Zhao", "affiliations": ["Beijing Institute of Technology"], "personId": "kangfei-zhao" } ], "affiliationSource": "https://arxiv.org/html/2603.11622v1" }, { "id": "nousdb", "catalogIds": ["nousdb"], "title": "NousDB - A Fast Query Engine for Semantic Analytics", "kind": "paper", "scope": "core", "date": "2026-10-20", "topic": "Research engine", "url": "https://arxiv.org/abs/2610.28551v2", "metadataSource": "https://arxiv.org/abs/2610.28551", "checkedDate": "2026-10-25", "authors": [ { "name": "Christos Tsapelas", "affiliations": [ "National and Kapodistrian University of Athens", "Athena Research Center" ], "personId": "christos-tsapelas" }, { "name": "Georgia Koutrika", "affiliations": ["Athena Research Center"], "personId": "georgia-koutrika" }, { "name": "Yannis Ioannidis", "affiliations": [ "National and Kapodistrian University of Athens", "Athena Research Center" ], "personId": "yannis-ioannidis" } ], "affiliationSource": "https://arxiv.org/html/2610.28551v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "jevdb", "catalogIds": ["jevdb"], "title": "Prune First, Decide Fast: Scalable Semantic Query Processing with JEVDB", "kind": "paper", "scope": "core", "date": "2026-10-01", "topic": "Research engine", "url": "https://arxiv.org/abs/2610.02046v1", "metadataSource": "https://arxiv.org/abs/2610.02046", "checkedDate": "2026-10-25", "authors": [ { "name": "Zhengle Wang", "affiliations": ["Purdue University"], "personId": "zhengle-wang" }, { "name": "Hanxu Yan", "affiliations": ["Purdue University"], "personId": "hanxu-yan" }, { "name": "Fuheng Zhao", "affiliations": ["University of Utah"], "personId": "fuheng-zhao" }, { "name": "Chunwei Liu", "affiliations": ["Purdue University"], "personId": "chunwei-liu" } ], "affiliationSource": "https://arxiv.org/pdf/2610.02046v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "semviews", "catalogIds": ["semviews"], "title": "Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries", "kind": "paper", "scope": "core", "date": "2026-10-08", "topic": "Optimization", "url": "https://arxiv.org/abs/2610.12768v1", "metadataSource": "https://arxiv.org/abs/2610.12768", "checkedDate": "2026-10-25", "authors": [ { "name": "Oktie Hassanzadeh", "affiliations": ["IBM"], "personId": "oktie-hassanzadeh" }, { "name": "Dharmashankar Subramanian", "affiliations": ["IBM"], "personId": "dharmashankar-subramanian" } ], "affiliationSource": "https://arxiv.org/html/2610.12768v1" }, { "id": "run-to-run-variance", "catalogIds": ["run-to-run-variance"], "title": "Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing", "kind": "paper", "scope": "core", "date": "2026-10-09", "topic": "Evaluation study", "url": "https://arxiv.org/abs/2610.13823v1", "metadataSource": "https://arxiv.org/abs/2610.13823", "checkedDate": "2026-10-25", "authors": [ { "name": "Oktie Hassanzadeh", "affiliations": ["IBM"], "personId": "oktie-hassanzadeh" }, { "name": "Dharmashankar Subramanian", "affiliations": ["IBM"], "personId": "dharmashankar-subramanian" } ], "affiliationSource": "https://arxiv.org/html/2610.13823v1" }, { "id": "sembaker", "catalogIds": ["sembaker"], "title": "From Interpretation to Compilation: A Compilation-Based Execution Engine for Semantic Operator Systems", "kind": "paper", "scope": "core", "date": "2026-08-07", "topic": "Optimization", "url": "https://arxiv.org/abs/2608.06677v1", "metadataSource": "https://arxiv.org/abs/2608.06677", "checkedDate": "2026-10-25", "authors": [ { "name": "Wenkai Dong", "affiliations": ["University of Hawaii at Manoa"], "personId": "wenkai-dong" }, { "name": "Yifan Wang", "affiliations": ["University of Hawaii at Manoa"], "personId": "yifan-wang" } ], "affiliationSource": "https://arxiv.org/html/2608.06677v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "kalypso", "catalogIds": ["kalypso"], "title": "Kalypso: Relational LLM Serving", "kind": "paper", "scope": "core", "date": "2026-07-26", "topic": "Optimization", "url": "https://arxiv.org/abs/2607.23815v2", "metadataSource": "https://arxiv.org/abs/2607.23815", "checkedDate": "2026-10-25", "authors": [ { "name": "Hojae Son", "affiliations": ["University of Massachusetts Amherst"], "personId": "hojae-son" }, { "name": "Md Ashraful Islam", "affiliations": ["University of Massachusetts Amherst"], "personId": "md-ashraful-islam" }, { "name": "Huy Gia Cao", "affiliations": ["University of Massachusetts Amherst"], "personId": "huy-gia-cao" }, { "name": "Hui Guan", "affiliations": ["University of Massachusetts Amherst"], "personId": "hui-guan" }, { "name": "Marco Serafini", "affiliations": ["University of Massachusetts Amherst"], "personId": "marco-serafini" } ], "affiliationSource": "https://arxiv.org/html/2607.23815v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "flockmtl", "catalogIds": ["flockmtl"], "title": "Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB", "kind": "paper", "scope": "core", "date": "2025-04-01", "topic": "Research engine", "url": "https://arxiv.org/abs/2504.01157v1", "metadataSource": "https://arxiv.org/abs/2504.01157", "checkedDate": "2026-10-25", "authors": [ { "name": "Anas Dorbani", "affiliations": ["Polytechnique Montréal"], "personId": "anas-dorbani" }, { "name": "Sunny Yasser", "affiliations": ["Polytechnique Montréal"], "personId": "sunny-yasser" }, { "name": "Jimmy Lin", "affiliations": ["University of Waterloo"], "personId": "jimmy-lin" }, { "name": "Amine Mhedhbi", "affiliations": ["Polytechnique Montréal"], "personId": "amine-mhedhbi" } ], "affiliationSource": "https://arxiv.org/html/2504.01157v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ipdb", "catalogIds": ["ipdb"], "title": "iPDB -- Optimizing Semantic SQL Queries", "kind": "paper", "scope": "core", "date": "2026-01-23", "topic": "Research engine", "url": "https://arxiv.org/abs/2601.16432v4", "metadataSource": "https://arxiv.org/abs/2601.16432", "checkedDate": "2026-10-25", "authors": [ { "name": "Udesh Kumarasinghe", "affiliations": ["Purdue University"], "personId": "udesh-kumarasinghe" }, { "name": "Tyler Liu", "affiliations": ["Purdue University"], "personId": "tyler-liu" }, { "name": "Ahmed R. Mahmood", "affiliations": ["Google"], "personId": "ahmed-r-mahmood" }, { "name": "Chunwei Liu", "affiliations": ["Purdue University"], "personId": "chunwei-liu" }, { "name": "Walid G. Aref", "affiliations": ["Purdue University"], "personId": "walid-g-aref" } ], "affiliationSource": "https://arxiv.org/html/2601.16432v4", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "plop", "catalogIds": ["plop"], "title": "PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query Plans", "kind": "paper", "scope": "core", "date": "2026-04-10", "topic": "Optimization", "url": "https://arxiv.org/abs/2604.09944v2", "metadataSource": "https://arxiv.org/abs/2604.09944", "checkedDate": "2026-10-25", "authors": [ { "name": "Qiuyang Mang", "affiliations": ["UC Berkeley"], "personId": "qiuyang-mang" }, { "name": "Yufan Xiang", "affiliations": ["University of Wisconsin-Madison"], "personId": "yufan-xiang" }, { "name": "Hangrui Zhou", "affiliations": ["UC Berkeley"], "personId": "hangrui-zhou" }, { "name": "Runyuan He", "affiliations": ["UC Berkeley"], "personId": "runyuan-he" }, { "name": "Jiaxiang Yu", "affiliations": ["UC Berkeley"], "personId": "jiaxiang-yu" }, { "name": "Hanchen Li", "affiliations": ["UC Berkeley"], "personId": "hanchen-li" }, { "name": "Aditya Parameswaran", "affiliations": ["UC Berkeley"], "personId": "aditya-g-parameswaran" }, { "name": "Alvin Cheung", "affiliations": ["UC Berkeley"], "personId": "alvin-cheung" } ], "affiliationSource": "https://arxiv.org/html/2604.09944v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "relational-llm-optimization", "catalogIds": ["relational-llm-optimization"], "title": "Optimizing LLM Queries in Relational Data Analytics Workloads", "kind": "paper", "scope": "core", "date": "2024-03-09", "topic": "Inference optimization", "url": "https://arxiv.org/abs/2403.05821v2", "metadataSource": "https://arxiv.org/abs/2403.05821", "checkedDate": "2026-10-25", "authors": [ { "name": "Shu Liu", "affiliations": ["UC Berkeley"], "personId": "shu-liu" }, { "name": "Asim Biswal", "affiliations": ["UC Berkeley"], "personId": "asim-biswal" }, { "name": "Amog Kamsetty", "affiliations": ["UC Berkeley"], "personId": "amog-kamsetty" }, { "name": "Audrey Cheng", "affiliations": ["UC Berkeley"], "personId": "audrey-cheng" }, { "name": "Luis Gaspar Schroeder", "affiliations": ["UC Berkeley", "Technical University of Munich"], "personId": "luis-gaspar-schroeder" }, { "name": "Liana Patel", "affiliations": ["Stanford University"], "personId": "liana-patel" }, { "name": "Shiyi Cao", "affiliations": ["UC Berkeley"], "personId": "shiyi-cao" }, { "name": "Xiangxi Mo", "affiliations": ["UC Berkeley"], "personId": "xiangxi-mo" }, { "name": "Ion Stoica", "affiliations": ["UC Berkeley"], "personId": "ion-stoica" }, { "name": "Joseph E. Gonzalez", "affiliations": ["UC Berkeley"], "personId": "joseph-e-gonzalez" }, { "name": "Matei Zaharia", "affiliations": ["UC Berkeley"], "personId": "matei-zaharia" } ], "affiliationSource": "https://arxiv.org/html/2403.05821v2" }, { "id": "llm-order-by", "catalogIds": ["llm-order-by"], "title": "Access Paths for Efficient Ordering with Large Language Models", "kind": "paper", "scope": "core", "date": "2025-08-30", "topic": "Optimization", "url": "https://arxiv.org/abs/2509.00303v5", "metadataSource": "https://arxiv.org/abs/2509.00303", "checkedDate": "2026-10-25", "authors": [ { "name": "Fuheng Zhao", "affiliations": ["University of Utah"], "personId": "fuheng-zhao" }, { "name": "Jiayue Chen", "affiliations": ["University of Chicago"], "personId": "jiayue-chen" }, { "name": "Yiming Pan", "affiliations": ["UCLA"], "personId": "yiming-pan" }, { "name": "Tahseen Rabbani", "affiliations": ["University of Chicago"], "personId": "tahseen-rabbani" }, { "name": "Sohaib", "affiliations": ["UC Santa Barbara"], "personId": "sohaib" }, { "name": "Divyakant Agrawal", "affiliations": ["UC Santa Barbara"], "personId": "divyakant-agrawal" }, { "name": "Amr El Abbadi", "affiliations": ["UC Santa Barbara"], "personId": "amr-el-abbadi" }, { "name": "Paritosh Aggarwal", "affiliations": ["Snowflake"], "personId": "paritosh-aggarwal" }, { "name": "Anupam Datta", "affiliations": ["Snowflake"], "personId": "anupam-datta" }, { "name": "Dimitris Tsirogiannis", "affiliations": ["Snowflake"], "personId": "dimitris-tsirogiannis" } ], "affiliationSource": "https://arxiv.org/html/2509.00303v5" }, { "id": "larch", "catalogIds": ["larch"], "title": "Larch: Learned Query Optimization for Semantic Predicates", "kind": "paper", "scope": "core", "date": "2026-06-06", "topic": "Optimization", "url": "https://arxiv.org/abs/2606.07923v1", "metadataSource": "https://arxiv.org/abs/2606.07923", "checkedDate": "2026-10-25", "authors": [ { "name": "Fuheng Zhao", "affiliations": ["Snowflake"], "personId": "fuheng-zhao" }, { "name": "Pawel Liskowski", "affiliations": ["Snowflake"], "personId": "pawel-liskowski" }, { "name": "Zihan Li", "affiliations": ["Snowflake"], "personId": "zihan-li" }, { "name": "Benjamin Han", "affiliations": ["Snowflake"], "personId": "benjamin-han" }, { "name": "Puxuan Yu", "affiliations": ["Snowflake"], "personId": "puxuan-yu" }, { "name": "Varich Boonsanong", "affiliations": ["Snowflake"], "personId": "varich-boonsanong" }, { "name": "Dimitris Tsirogiannis", "affiliations": ["Snowflake"], "personId": "dimitris-tsirogiannis" }, { "name": "Anupam Datta", "affiliations": ["Snowflake"], "personId": "anupam-datta" } ], "affiliationSource": "https://arxiv.org/html/2606.07923v1" }, { "id": "fast-semantic-filtering", "catalogIds": ["fast-semantic-filtering"], "title": "Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method", "kind": "paper", "scope": "core", "date": "2026-06-06", "topic": "Optimization", "url": "https://arxiv.org/abs/2606.08090v2", "metadataSource": "https://arxiv.org/abs/2606.08090", "checkedDate": "2026-10-25", "authors": [ { "name": "Kyoungmin Kim", "affiliations": ["EPFL"], "personId": "kyoungmin-kim" }, { "name": "Martin Catheland", "affiliations": ["EPFL"], "personId": "martin-catheland" }, { "name": "Anastasia Ailamaki", "affiliations": ["EPFL"], "personId": "anastasia-ailamaki" } ], "affiliationSource": "https://arxiv.org/html/2606.08090v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "semjoin", "catalogIds": ["semjoin"], "title": "SemJoin: Semantic Join Optimization", "kind": "paper", "scope": "core", "date": "2026-06-28", "topic": "Optimization", "url": "https://arxiv.org/abs/2606.29532v1", "metadataSource": "https://arxiv.org/abs/2606.29532", "checkedDate": "2026-10-25", "authors": [ { "name": "Christopher Gou", "affiliations": ["Purdue University"], "personId": "christopher-gou" }, { "name": "Aditya Banerjee", "affiliations": ["Purdue University"], "personId": "aditya-banerjee" }, { "name": "Jiaxuan Wang", "affiliations": ["Purdue University"], "personId": "jiaxuan-wang" }, { "name": "Chunwei Liu", "affiliations": ["Purdue University"], "personId": "chunwei-liu" } ], "affiliationSource": "https://arxiv.org/html/2606.29532v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "uda-bench", "catalogIds": ["uda-bench"], "title": "Unstructured Data Analysis using LLMs: A Comprehensive Benchmark", "kind": "paper", "scope": "core", "date": "2025-10-31", "topic": "Evaluation", "url": "https://arxiv.org/abs/2510.27119v1", "metadataSource": "https://arxiv.org/abs/2510.27119", "checkedDate": "2026-10-25", "authors": [ { "name": "Qiyan Deng", "affiliations": ["Beijing Institute of Technology"], "personId": "qiyan-deng" }, { "name": "Jianhui Li", "affiliations": ["Beijing Institute of Technology"], "personId": "jianhui-li" }, { "name": "Chengliang Chai", "affiliations": ["Beijing Institute of Technology"], "personId": "chengliang-chai" }, { "name": "Jinqi Liu", "affiliations": ["Beijing Institute of Technology"], "personId": "jinqi-liu" }, { "name": "Junzhi She", "affiliations": ["Beijing Institute of Technology"], "personId": "junzhi-she" }, { "name": "Kaisen Jin", "affiliations": ["Beijing Institute of Technology"], "personId": "kaisen-jin" }, { "name": "Zhaoze Sun", "affiliations": ["Beijing Institute of Technology"], "personId": "zhaoze-sun" }, { "name": "Yuhao Deng", "affiliations": ["Beijing Institute of Technology"], "personId": "yuhao-deng" }, { "name": "Jia Yuan", "affiliations": ["University of Arizona"], "personId": "jia-yuan" }, { "name": "Ye Yuan", "affiliations": ["Beijing Institute of Technology"], "personId": "ye-yuan" }, { "name": "Guoren Wang", "affiliations": ["Beijing Institute of Technology"], "personId": "guoren-wang" }, { "name": "Lei Cao", "affiliations": ["University of Arizona", "MIT"], "personId": "lei-cao" } ], "affiliationSource": "https://arxiv.org/html/2510.27119v1" }, { "id": "spider2-aifunc", "catalogIds": ["spider2-aifunc"], "title": "Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows", "kind": "paper", "scope": "core", "date": "2026-07-07", "topic": "Benchmark", "url": "https://arxiv.org/abs/2607.06229v1", "metadataSource": "https://arxiv.org/abs/2607.06229", "checkedDate": "2026-10-25", "authors": [ { "name": "Tianyang Liu", "affiliations": ["UC San Diego"], "personId": "tianyang-liu" }, { "name": "Canwen Xu", "affiliations": ["Snowflake"], "personId": "canwen-xu" }, { "name": "Fangyu Lei", "affiliations": ["University of Hong Kong"], "personId": "fangyu-lei" }, { "name": "Nikki Lijing Kuang", "affiliations": ["Snowflake"], "personId": "nikki-lijing-kuang" }, { "name": "Jixuan Chen", "affiliations": ["UC San Diego"], "personId": "jixuan-chen" }, { "name": "Tao Yu", "affiliations": ["University of Hong Kong"], "personId": "tao-yu" }, { "name": "Julian McAuley", "affiliations": ["UC San Diego"], "personId": "julian-mcauley" }, { "name": "Zhewei Yao", "affiliations": ["Snowflake"], "personId": "zhewei-yao" }, { "name": "Yuxiong He", "affiliations": ["Snowflake"], "personId": "yuxiong-he" } ], "affiliationSource": "https://arxiv.org/html/2607.06229v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "vectorsqlbench", "catalogIds": ["vectorsqlbench"], "title": "Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL Queries", "kind": "paper", "scope": "core", "date": "2025-06-29", "topic": "Benchmark", "url": "https://arxiv.org/abs/2506.23071v2", "metadataSource": "https://arxiv.org/abs/2506.23071", "checkedDate": "2026-10-25", "authors": [ { "name": "Zhengren Wang", "affiliations": ["Peking University"], "personId": "zhengren-wang" }, { "name": "Dongwen Yao", "affiliations": ["Shanghai Jiao Tong University"], "personId": "dongwen-yao" }, { "name": "Bozhou Li", "affiliations": ["Peking University"], "personId": "bozhou-li" }, { "name": "Dongsheng Ma", "affiliations": ["Peking University"], "personId": "dongsheng-ma" }, { "name": "Bo Li", "affiliations": ["Peking University"], "personId": "bo-li" }, { "name": "Zhiyu Li", "affiliations": ["Institute for Advanced Algorithms Research, Shanghai"], "personId": "zhiyu-li" }, { "name": "Feiyu Xiong", "affiliations": ["Institute for Advanced Algorithms Research, Shanghai"], "personId": "feiyu-xiong" }, { "name": "Bin Cui", "affiliations": ["Peking University"], "personId": "bin-cui" }, { "name": "Linpeng Tang", "affiliations": [ "OriginHub Technology", "Institute for Advanced Algorithms Research, Shanghai" ], "personId": "linpeng-tang" }, { "name": "Wentao Zhang", "affiliations": ["Peking University", "OriginHub Technology", "Zhongguancun Academy"], "personId": "wentao-zhang" } ], "affiliationSource": "https://arxiv.org/pdf/2506.23071v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "hybrid-deep-research", "catalogIds": ["hybrid-deep-research"], "title": "Benchmarking Hybrid Deep Research Across Database Querying and Web Search", "kind": "paper", "scope": "core", "date": "2026-09-08", "topic": "Benchmark", "url": "https://arxiv.org/abs/2609.09410v1", "metadataSource": "https://arxiv.org/abs/2609.09410", "checkedDate": "2026-10-25", "authors": [ { "name": "Ruofan Wu", "affiliations": ["University of Houston"], "personId": "ruofan-wu" }, { "name": "Peiran Xu", "affiliations": ["UCLA"], "personId": "peiran-xu" }, { "name": "Xiaolong Li", "affiliations": ["University of Hong Kong"], "personId": "xiaolong-li" }, { "name": "Fan Shu", "affiliations": ["University of Houston"], "personId": "fan-shu" }, { "name": "Soyoung Yoon", "affiliations": ["Seoul National University"], "personId": "soyoung-yoon" }, { "name": "Yite Wang", "affiliations": ["Snowflake"], "personId": "yite-wang" }, { "name": "Xiaodong Yu", "affiliations": ["Snowflake"], "personId": "xiaodong-yu" }, { "name": "Boyi Liu", "affiliations": ["Snowflake"], "personId": "boyi-liu" }, { "name": "Feng Yan", "affiliations": ["University of Houston"], "personId": "feng-yan" }, { "name": "Debiao Li", "affiliations": ["UCLA"], "personId": "debiao-li" }, { "name": "Yuxiong He", "affiliations": ["Snowflake"], "personId": "yuxiong-he" }, { "name": "Zhewei Yao", "affiliations": ["Snowflake"], "personId": "zhewei-yao" } ], "affiliationSource": "https://arxiv.org/pdf/2609.09410v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "stochastic-shift", "catalogIds": ["stochastic-shift"], "title": "The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI Operators", "kind": "paper", "scope": "core", "date": "2026-09-17", "topic": "Evaluation study", "url": "https://arxiv.org/abs/2609.21133v1", "metadataSource": "https://arxiv.org/abs/2609.21133", "checkedDate": "2026-10-25", "authors": [ { "name": "Tarfah Alrashed", "affiliations": ["Google"], "personId": "tarfah-alrashed" }, { "name": "Fatma Ozcan", "affiliations": ["Google"], "personId": "fatma-ozcan" }, { "name": "Per Jacobsson", "affiliations": ["Google"], "personId": "per-jacobsson" }, { "name": "Tal Neiman", "affiliations": ["Google"], "personId": "tal-neiman" }, { "name": "Xianshun Chen", "affiliations": ["Google"], "personId": "xianshun-chen" } ], "affiliationSource": "https://arxiv.org/html/2609.21133v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-e4aa4c5754b8", "catalogIds": ["ref-e4aa4c5754b8"], "title": "Demo of SemWeave: Semantic Common Expressions for LLM-powered Query Processing", "kind": "paper", "scope": "core", "date": "2026-05-30", "topic": "Core SQPE papers", "url": "https://doi.org/10.1145/3788853.3801593", "metadataSource": "https://api.crossref.org/works/10.1145%2F3788853.3801593", "checkedDate": "2026-10-25", "authors": [ { "name": "Md. Tareq Mahmood", "affiliations": ["University of Wisconsin-Madison, Madison, WI, USA"], "personId": "md-tareq-mahmood" }, { "name": "Venkatesh Emani", "affiliations": ["Microsoft Gray Systems Lab, Madison, WI, USA"], "personId": "venkatesh-emani" }, { "name": "Hangdong Zhao", "affiliations": ["Microsoft Gray Systems Lab, Redmond, WA, USA"], "personId": "hangdong-zhao" }, { "name": "Shivaram Venkataraman", "affiliations": ["University of Wisconsin-Madison, Madison, WI, USA"], "personId": "shivaram-venkataraman" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F3788853.3801593" }, { "id": "ref-0dd51ec5b206", "catalogIds": ["ref-0dd51ec5b206"], "title": "100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]", "kind": "paper", "scope": "core", "date": "2026-05-18", "topic": "Core SQPE papers", "url": "https://doi.org/10.1145/3802002", "metadataSource": "https://api.crossref.org/works/10.1145%2F3802002", "checkedDate": "2026-10-25", "authors": [ { "name": "Yeounoh Chung", "affiliations": ["Google"], "personId": "yeounoh-chung" }, { "name": "Rushabh Desai", "affiliations": ["Google"], "personId": "rushabh-desai" }, { "name": "Jian He", "affiliations": ["Google"], "personId": "jian-he" }, { "name": "Yu Xiao", "affiliations": ["Google"], "personId": "yu-xiao" }, { "name": "Thibaud Hottelier", "affiliations": ["Google"], "personId": "thibaud-hottelier" }, { "name": "Yves-Laurent Kom Samo", "affiliations": ["Google"], "personId": "yves-laurent-kom-samo" }, { "name": "Pushkar Khadilkar", "affiliations": ["Google"], "personId": "pushkar-khadilkar" }, { "name": "Xianshun Chen", "affiliations": ["Google"], "personId": "xianshun-chen" }, { "name": "Sam Idicula", "affiliations": ["Google"], "personId": "sam-idicula" }, { "name": "Fatma Ozcan", "affiliations": ["Google"], "personId": "fatma-ozcan" }, { "name": "Alon Halevy", "affiliations": ["Google"], "personId": "alon-halevy" }, { "name": "Yannis Papakonstantinou", "affiliations": ["Google"], "personId": "yannis-papakonstantinou" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F3802002" }, { "id": "arxiv-2511-07663", "catalogIds": ["arxiv-2511-07663"], "title": "Cortex AISQL: A Production SQL Engine for Unstructured Data", "kind": "paper", "scope": "core", "date": "2025-11-10", "topic": "Core SQPE papers", "url": "https://arxiv.org/abs/2511.07663v3", "metadataSource": "https://arxiv.org/abs/2511.07663", "checkedDate": "2026-10-25", "authors": [ { "name": "Paweł Liskowski", "affiliations": ["Snowflake"], "personId": "pawel-liskowski" }, { "name": "Benjamin Han", "affiliations": ["Snowflake"], "personId": "benjamin-han" }, { "name": "Paritosh Aggarwal", "affiliations": ["Snowflake"], "personId": "paritosh-aggarwal" }, { "name": "Bowei Chen", "affiliations": ["Snowflake"], "personId": "bowei-chen" }, { "name": "Boxin Jiang", "affiliations": ["Snowflake"], "personId": "boxin-jiang" }, { "name": "Nitish Jindal", "affiliations": ["Snowflake"], "personId": "nitish-jindal" }, { "name": "Zihan Li", "affiliations": ["Snowflake"], "personId": "zihan-li" }, { "name": "Aaron Lin", "affiliations": ["Snowflake"], "personId": "aaron-lin" }, { "name": "Kyle Schmaus", "affiliations": ["Snowflake"], "personId": "kyle-schmaus" }, { "name": "Jay Tayade", "affiliations": ["Snowflake"], "personId": "jay-tayade" }, { "name": "Weicheng Zhao", "affiliations": ["Snowflake"], "personId": "weicheng-zhao" }, { "name": "Anupam Datta", "affiliations": ["Snowflake"], "personId": "anupam-datta" }, { "name": "Nathan Wiegand", "affiliations": ["Snowflake"], "personId": "nathan-wiegand" }, { "name": "Dimitris Tsirogiannis", "affiliations": ["Snowflake"], "personId": "dimitris-tsirogiannis" } ], "affiliationSource": "https://arxiv.org/html/2511.07663v3" }, { "id": "arxiv-2602-01701", "catalogIds": ["arxiv-2602-01701"], "title": "Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal Data", "kind": "paper", "scope": "core", "date": "2026-02-02", "topic": "Core SQPE papers", "url": "https://arxiv.org/abs/2602.01701v2", "metadataSource": "https://arxiv.org/abs/2602.01701", "checkedDate": "2026-10-25", "authors": [ { "name": "Ruyu Li", "affiliations": ["University of Hawaii at Manoa"], "personId": "ruyu-li" }, { "name": "Tinghui Zhang", "affiliations": ["University of Florida"], "personId": "tinghui-zhang" }, { "name": "Haodi Ma", "affiliations": ["University of Florida"], "personId": "haodi-ma" }, { "name": "Daisy Zhe Wang", "affiliations": ["University of Florida"], "personId": "daisy-zhe-wang" }, { "name": "Yifan Wang", "affiliations": ["University of Hawaii at Manoa"], "personId": "yifan-wang" } ], "affiliationSource": "https://arxiv.org/html/2602.01701v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2606-29151", "catalogIds": ["arxiv-2606-29151"], "title": "CADENZA: Compiling Natural-Language Intent into Task-Specific Operator DAGs for Semantic Query Processing", "kind": "paper", "scope": "core", "date": "2026-06-28", "topic": "Optimization", "url": "https://arxiv.org/abs/2606.29151v3", "metadataSource": "https://arxiv.org/abs/2606.29151", "checkedDate": "2026-10-25", "authors": [ { "name": "Jaehyun Ha", "affiliations": ["POSTECH"], "personId": "jaehyun-ha" }, { "name": "Yongjoo Park", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "yongjoo-park" }, { "name": "Wook-Shin Han", "affiliations": ["POSTECH"], "personId": "wook-shin-han" } ], "affiliationSource": "https://arxiv.org/html/2606.29151v3", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2512-05399", "catalogIds": ["arxiv-2512-05399"], "title": "Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees", "kind": "paper", "scope": "core", "date": "2025-12-05", "topic": "Semantic joins", "url": "https://arxiv.org/abs/2512.05399v1", "metadataSource": "https://arxiv.org/abs/2512.05399", "checkedDate": "2026-10-25", "authors": [ { "name": "Sepanta Zeighami", "affiliations": ["UC Berkeley"], "personId": "sepanta-zeighami" }, { "name": "Shreya Shankar", "affiliations": ["UC Berkeley"], "personId": "shreya-shankar" }, { "name": "Aditya Parameswaran", "affiliations": ["UC Berkeley"], "personId": "aditya-g-parameswaran" } ], "affiliationSource": "https://arxiv.org/html/2512.05399v1" }, { "id": "ref-43d0f45c6e32", "catalogIds": ["ref-43d0f45c6e32"], "title": "Accelerating Approximate Analytical Join Queries over Unstructured Data with Statistical Guarantees", "kind": "paper", "scope": "related", "date": "2026-05-18", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://doi.org/10.1145/3802004", "metadataSource": "https://api.crossref.org/works/10.1145%2F3802004", "checkedDate": "2026-10-25", "authors": [ { "name": "Yuxuan Zhu", "affiliations": ["University of Illinois Urbana-Champaign, Urbana, USA"], "personId": "yuxuan-zhu" }, { "name": "Tengjun Jin", "affiliations": ["University of Illinois Urbana-Champaign, Urbana, USA"], "personId": "tengjun-jin" }, { "name": "Chenghao Mo", "affiliations": ["University of Illinois Urbana-Champaign, Urbana, USA"], "personId": "chenghao-mo" }, { "name": "Daniel Kang", "affiliations": ["University of Illinois Urbana-Champaign, Urbana, USA"], "personId": "daniel-kang" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F3802004" }, { "id": "arxiv-2603-17223", "catalogIds": ["arxiv-2603-17223"], "title": "ListK: Semantic ORDER BY and LIMIT K with Listwise Prompting", "kind": "paper", "scope": "related", "date": "2026-03-18", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2603.17223v1", "metadataSource": "https://arxiv.org/abs/2603.17223", "checkedDate": "2026-10-25", "authors": [ { "name": "Jason Shin", "affiliations": ["University of Rochester"], "personId": "jason-shin" }, { "name": "Jiwon Chang", "affiliations": ["University of Rochester"], "personId": "jiwon-chang" }, { "name": "Fatemeh Nargesian", "affiliations": ["University of Rochester"], "personId": "fatemeh-nargesian" } ], "affiliationSource": "https://arxiv.org/html/2603.17223v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2503-20119", "catalogIds": ["arxiv-2503-20119"], "title": "Approximating Opaque Top-k Queries", "kind": "paper", "scope": "related", "date": "2025-03-25", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2503.20119v1", "metadataSource": "https://arxiv.org/abs/2503.20119", "checkedDate": "2026-10-25", "authors": [ { "name": "Jiwon Chang", "affiliations": ["University of Rochester"], "personId": "jiwon-chang" }, { "name": "Fatemeh Nargesian", "affiliations": ["University of Rochester"], "personId": "fatemeh-nargesian" } ], "affiliationSource": "https://arxiv.org/html/2503.20119v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2502-18470", "catalogIds": ["arxiv-2502-18470"], "title": "RankLLM: A Python Package for Reranking with LLMs", "kind": "paper", "scope": "related", "date": "2025-05-25", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2505.19284v1", "metadataSource": "https://arxiv.org/abs/2505.19284", "checkedDate": "2026-10-25", "authors": [ { "name": "Sahel Sharifymoghaddam", "affiliations": ["University of Waterloo"], "personId": "sahel-sharifymoghaddam" }, { "name": "Ronak Pradeep", "affiliations": ["University of Waterloo"], "personId": "ronak-pradeep" }, { "name": "Andre Slavescu", "affiliations": ["University of Waterloo"], "personId": "andre-slavescu" }, { "name": "Ryan Nguyen", "affiliations": ["University of Waterloo"], "personId": "ryan-nguyen" }, { "name": "Andrew Xu", "affiliations": ["University of Waterloo"], "personId": "andrew-xu" }, { "name": "Zijian Chen", "affiliations": ["University of Waterloo"], "personId": "zijian-chen" }, { "name": "Yilin Zhang", "affiliations": ["University of Waterloo"], "personId": "yilin-zhang" }, { "name": "Yidi Chen", "affiliations": ["University of Waterloo"], "personId": "yidi-chen" }, { "name": "Jasper Xian", "affiliations": ["University of Waterloo"], "personId": "jasper-xian" }, { "name": "Jimmy Lin", "affiliations": ["University of Waterloo"], "personId": "jimmy-lin" } ], "affiliationSource": "https://arxiv.org/html/2505.19284v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2312-02724", "catalogIds": ["arxiv-2312-02724"], "title": "RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!", "kind": "paper", "scope": "related", "date": "2023-12-05", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2312.02724v1", "metadataSource": "https://arxiv.org/abs/2312.02724", "checkedDate": "2026-10-25", "authors": [ { "name": "Ronak Pradeep", "affiliations": ["University of Waterloo"], "personId": "ronak-pradeep" }, { "name": "Sahel Sharifymoghaddam", "affiliations": ["University of Waterloo"], "personId": "sahel-sharifymoghaddam" }, { "name": "Jimmy Lin", "affiliations": ["University of Waterloo"], "personId": "jimmy-lin" } ], "affiliationSource": "https://arxiv.org/html/2312.02724v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2607-00254", "catalogIds": ["arxiv-2607-00254"], "title": "Query-Centric Optimization of AI Workflows via Approximate Query Processing and Proxy Models", "kind": "paper", "scope": "related", "date": "2026-06-30", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2607.00254v2", "metadataSource": "https://arxiv.org/abs/2607.00254", "checkedDate": "2026-10-25", "authors": [ { "name": "Huayi Wang", "affiliations": ["Georgia Institute of Technology"], "personId": "huayi-wang" }, { "name": "Jun Xu", "affiliations": ["Georgia Institute of Technology"], "personId": "jun-xu" }, { "name": "Gromit Yeuk-Yin Chan", "affiliations": ["Adobe Research"], "personId": "gromit-yeuk-yin-chan" } ], "affiliationSource": "https://arxiv.org/html/2607.00254v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2403-14902", "catalogIds": ["arxiv-2403-14902"], "title": "Hydro: Adaptive Query Processing of ML Queries", "kind": "paper", "scope": "related", "date": "2024-03-22", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2403.14902v1", "metadataSource": "https://arxiv.org/abs/2403.14902", "checkedDate": "2026-10-25", "authors": [ { "name": "Gaurav Tarlok Kakkar", "affiliations": ["Georgia Institute of Technology"], "personId": "gaurav-tarlok-kakkar" }, { "name": "Jiashen Cao", "affiliations": ["Georgia Institute of Technology"], "personId": "jiashen-cao" }, { "name": "Aubhro Sengupta", "affiliations": ["Georgia Institute of Technology"], "personId": "aubhro-sengupta" }, { "name": "Joy Arulraj", "affiliations": ["Georgia Institute of Technology"], "personId": "joy-arulraj" }, { "name": "Hyesoon Kim", "affiliations": ["Georgia Institute of Technology"], "personId": "hyesoon-kim" } ], "affiliationSource": "https://arxiv.org/html/2403.14902v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-1911-00231", "catalogIds": ["arxiv-1911-00231"], "title": "Extending Relational Query Processing with ML Inference", "kind": "paper", "scope": "related", "date": "2019-11-01", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/1911.00231v1", "metadataSource": "https://arxiv.org/abs/1911.00231", "checkedDate": "2026-10-25", "authors": [ { "name": "Konstantinos Karanasos", "affiliations": ["Microsoft"], "personId": "konstantinos-karanasos" }, { "name": "Matteo Interlandi", "affiliations": ["Microsoft"], "personId": "matteo-interlandi" }, { "name": "Doris Xin", "affiliations": ["UC Berkeley"], "personId": "doris-xin" }, { "name": "Fotis Psallidas", "affiliations": ["Microsoft"], "personId": "fotis-psallidas" }, { "name": "Rathijit Sen", "affiliations": ["Microsoft"], "personId": "rathijit-sen" }, { "name": "Kwanghyun Park", "affiliations": ["Microsoft"], "personId": "kwanghyun-park" }, { "name": "Ivan Popivanov", "affiliations": ["Microsoft"], "personId": "ivan-popivanov" }, { "name": "Supun Nakandal", "affiliations": ["UC San Diego"], "personId": "supun-nakandal" }, { "name": "Subru Krishnan", "affiliations": ["Microsoft"], "personId": "subru-krishnan" }, { "name": "Markus Weimer", "affiliations": ["Microsoft"], "personId": "markus-weimer" }, { "name": "Yuan Yu", "affiliations": ["Microsoft"], "personId": "yuan-yu" }, { "name": "Raghu Ramakrishnan", "affiliations": ["Microsoft"], "personId": "raghu-ramakrishnan" }, { "name": "Carlo Curino", "affiliations": ["Microsoft"], "personId": "carlo-curino" } ], "affiliationSource": "https://arxiv.org/html/1911.00231v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2312-17355", "catalogIds": ["arxiv-2312-17355"], "title": "The Duck's Brain: Training and Inference of Neural Networks in Modern Database Engines", "kind": "paper", "scope": "related", "date": "2023-12-28", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2312.17355v1", "metadataSource": "https://arxiv.org/abs/2312.17355", "checkedDate": "2026-10-25", "authors": [ { "name": "Maximilian E. Schüle", "affiliations": ["University of Bamberg"], "personId": "maximilian-e-schule" }, { "name": "Thomas Neumann", "affiliations": ["Technical University of Munich"], "personId": "thomas-neumann" }, { "name": "Alfons Kemper", "affiliations": ["Technical University of Munich"], "personId": "alfons-kemper" } ], "affiliationSource": "https://arxiv.org/pdf/2312.17355v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-a7c381b5e4ce", "catalogIds": ["ref-a7c381b5e4ce"], "title": "The MADlib analytics library: or MAD skills, the SQL", "kind": "paper", "scope": "related", "date": "2012-08", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://doi.org/10.14778/2367502.2367510", "metadataSource": "https://api.crossref.org/works/10.14778%2F2367502.2367510", "checkedDate": "2026-10-25", "authors": [ { "name": "Joseph M. Hellerstein", "affiliations": ["U.C. Berkeley"], "personId": "joseph-m-hellerstein" }, { "name": "Christoper Ré", "affiliations": ["U. Wisconsin"], "personId": "christoper-re" }, { "name": "Florian Schoppmann", "affiliations": ["Greenplum"], "personId": "florian-schoppmann" }, { "name": "Daisy Zhe Wang", "affiliations": ["U. Florida"], "personId": "daisy-zhe-wang" }, { "name": "Eugene Fratkin", "affiliations": ["Greenplum"], "personId": "eugene-fratkin" }, { "name": "Aleksander Gorajek", "affiliations": ["Greenplum"], "personId": "aleksander-gorajek" }, { "name": "Kee Siong Ng", "affiliations": ["Greenplum"], "personId": "kee-siong-ng" }, { "name": "Caleb Welton", "affiliations": ["Greenplum"], "personId": "caleb-welton" }, { "name": "Xixuan Feng", "affiliations": ["U. Wisconsin"], "personId": "xixuan-feng" }, { "name": "Kun Li", "affiliations": ["U. Florida"], "personId": "kun-li" }, { "name": "Arun Kumar", "affiliations": ["U. Wisconsin"], "personId": "arun-kumar" } ], "affiliationSource": "https://api.crossref.org/works/10.14778%2F2367502.2367510" }, { "id": "ref-3e4a67ac6d74", "catalogIds": ["ref-3e4a67ac6d74"], "title": "DuckDB: an Embeddable Analytical Database", "kind": "paper", "scope": "related", "date": "2019-06-25", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://doi.org/10.1145/3299869.3320212", "metadataSource": "https://api.crossref.org/works/10.1145%2F3299869.3320212", "checkedDate": "2026-10-25", "authors": [ { "name": "Mark Raasveldt", "affiliations": ["CWI, Amsterdam, Netherlands"], "personId": "mark-raasveldt" }, { "name": "Hannes Mühleisen", "affiliations": ["CWI, Amsterdam, Netherlands"], "personId": "hannes-muhleisen" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F3299869.3320212" }, { "id": "ref-84654a2d3434", "catalogIds": ["ref-84654a2d3434"], "title": "MonetDB/X100: Hyper-Pipelining Query Execution", "kind": "paper", "scope": "related", "date": "2005", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://www.cidrdb.org/cidr2005/papers/P19.pdf", "metadataSource": "https://www.cidrdb.org/cidr2005/papers/P19.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "Peter Boncz", "affiliations": ["CWI"], "personId": "peter-boncz" }, { "name": "Marcin Zukowski", "affiliations": ["CWI"], "personId": "marcin-zukowski" }, { "name": "Niels Nes", "affiliations": ["CWI"], "personId": "niels-nes" } ], "affiliationSource": "https://www.cidrdb.org/cidr2005/papers/P19.pdf" }, { "id": "ref-3dff26b27bff", "catalogIds": ["ref-3dff26b27bff"], "title": "BioDEX: Large-Scale Biomedical Adverse Drug Event Extraction for Real-World Pharmacovigilance", "kind": "paper", "scope": "related", "date": "2023", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://doi.org/10.18653/v1/2023.findings-emnlp.896", "metadataSource": "https://api.crossref.org/works/10.18653%2Fv1%2F2023.findings-emnlp.896", "checkedDate": "2026-10-25", "authors": [ { "name": "Karel D’Oosterlinck", "affiliations": ["Ghent University", "imec"], "personId": "karel-doosterlinck" }, { "name": "François Remy", "affiliations": ["Ghent University", "imec"], "personId": "francois-remy" }, { "name": "Johannes Deleu", "affiliations": ["Ghent University", "imec"], "personId": "johannes-deleu" }, { "name": "Thomas Demeester", "affiliations": ["Ghent University", "imec"], "personId": "thomas-demeester" }, { "name": "Chris Develder", "affiliations": ["Ghent University", "imec"], "personId": "chris-develder" }, { "name": "Klim Zaporojets", "affiliations": ["Aarhus University"], "personId": "klim-zaporojets" }, { "name": "Aneiss Ghodsi", "affiliations": ["Parexel AI Labs"], "personId": "aneiss-ghodsi" }, { "name": "Simon Ellershaw", "affiliations": ["Parexel AI Labs"], "personId": "simon-ellershaw" }, { "name": "Jack Collins", "affiliations": ["Parexel AI Labs"], "personId": "jack-collins" }, { "name": "Christopher Potts", "affiliations": ["Stanford University"], "personId": "christopher-potts" } ], "affiliationSource": "https://aclanthology.org/2023.findings-emnlp.896.pdf", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2510-08489", "catalogIds": ["arxiv-2510-08489"], "title": "Implementing Semantic Join Operators Efficiently", "kind": "paper", "scope": "related", "date": "2025-10-09", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2510.08489v1", "metadataSource": "https://arxiv.org/abs/2510.08489", "checkedDate": "2026-10-25", "authors": [ { "name": "Immanuel Trummer", "affiliations": ["Cornell University"], "personId": "immanuel-trummer" } ], "affiliationSource": "https://arxiv.org/html/2510.08489v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2505-14661", "catalogIds": ["arxiv-2505-14661"], "title": "Abacus: A Cost-Based Optimizer for Semantic Operator Systems", "kind": "paper", "scope": "related", "date": "2025-05-20", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2505.14661v3", "metadataSource": "https://arxiv.org/abs/2505.14661", "checkedDate": "2026-10-25", "authors": [ { "name": "Matthew Russo", "affiliations": ["MIT"], "personId": "matthew-russo" }, { "name": "Chunwei Liu", "affiliations": ["MIT"], "personId": "chunwei-liu" }, { "name": "Sivaprasad Sudhir", "affiliations": ["MIT"], "personId": "sivaprasad-sudhir" }, { "name": "Gerardo Vitagliano", "affiliations": ["MIT"], "personId": "gerardo-vitagliano" }, { "name": "Michael Cafarella", "affiliations": ["MIT"], "personId": "michael-cafarella" }, { "name": "Tim Kraska", "affiliations": ["MIT"], "personId": "tim-kraska" }, { "name": "Samuel Madden", "affiliations": ["MIT"], "personId": "samuel-madden" } ], "affiliationSource": "https://arxiv.org/html/2505.14661v3", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2507-06515", "catalogIds": ["arxiv-2507-06515"], "title": "QUEST: Query Optimization in Unstructured Document Analysis", "kind": "paper", "scope": "related", "date": "2025-07-09", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2507.06515v2", "metadataSource": "https://arxiv.org/abs/2507.06515", "checkedDate": "2026-10-25", "authors": [ { "name": "Zhaoze Sun", "affiliations": ["Beijing Institute of Technology"], "personId": "zhaoze-sun" }, { "name": "Qiyan Deng", "affiliations": ["Beijing Institute of Technology"], "personId": "qiyan-deng" }, { "name": "Chengliang Chai", "affiliations": ["Beijing Institute of Technology"], "personId": "chengliang-chai" }, { "name": "Kaisen Jin", "affiliations": ["Beijing Institute of Technology"], "personId": "kaisen-jin" }, { "name": "Xinyu Guo", "affiliations": ["University of Arizona"], "personId": "xinyu-guo" }, { "name": "Han Han", "affiliations": ["University of Arizona"], "personId": "han-han" }, { "name": "Ye Yuan", "affiliations": ["Beijing Institute of Technology"], "personId": "ye-yuan" }, { "name": "Guoren Wang", "affiliations": ["Beijing Institute of Technology"], "personId": "guoren-wang" }, { "name": "Lei Cao", "affiliations": ["MIT", "University of Arizona"], "personId": "lei-cao" } ], "affiliationSource": "https://arxiv.org/html/2507.06515v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2509-12610", "catalogIds": ["arxiv-2509-12610"], "title": "ScaleDoc: Scaling LLM-based Predicates over Large Document Collections", "kind": "paper", "scope": "related", "date": "2025-09-16", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2509.12610v2", "metadataSource": "https://arxiv.org/abs/2509.12610", "checkedDate": "2026-10-25", "authors": [ { "name": "Hengrui Zhang", "affiliations": ["Tsinghua University"], "personId": "hengrui-zhang" }, { "name": "Yulong Hui", "affiliations": ["Tsinghua University"], "personId": "yulong-hui" }, { "name": "Yihao Liu", "affiliations": ["Tsinghua University"], "personId": "yihao-liu" }, { "name": "Huanchen Zhang", "affiliations": ["Tsinghua University", "Shanghai Qi Zhi Institute"], "personId": "huanchen-zhang" } ], "affiliationSource": "https://arxiv.org/html/2509.12610v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2603-04799", "catalogIds": ["arxiv-2603-04799"], "title": "Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter Paradigm", "kind": "paper", "scope": "related", "date": "2026-03-05", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2603.04799v1", "metadataSource": "https://arxiv.org/abs/2603.04799", "checkedDate": "2026-10-25", "authors": [ { "name": "Nan Hou", "affiliations": ["The Chinese University of Hong Kong"], "personId": "nan-hou" }, { "name": "Kangfei Zhao", "affiliations": ["Beijing Institute of Technology"], "personId": "kangfei-zhao" }, { "name": "Jiadong Xie", "affiliations": ["The Chinese University of Hong Kong"], "personId": "jiadong-xie" }, { "name": "Jeffrey Xu Yu", "affiliations": ["HKUST (Guangzhou)"], "personId": "jeffrey-xu-yu" } ], "affiliationSource": "https://arxiv.org/html/2603.04799v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-21402d1d1aea", "catalogIds": ["ref-21402d1d1aea"], "title": "Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees", "kind": "paper", "scope": "related", "date": "2025-09-02", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2509.02896v2", "metadataSource": "https://arxiv.org/abs/2509.02896", "checkedDate": "2026-10-25", "authors": [ { "name": "Sepanta Zeighami", "affiliations": ["UC Berkeley"], "personId": "sepanta-zeighami" }, { "name": "Shreya Shankar", "affiliations": ["UC Berkeley"], "personId": "shreya-shankar" }, { "name": "Aditya Parameswaran", "affiliations": ["UC Berkeley"], "personId": "aditya-g-parameswaran" } ], "affiliationSource": "https://arxiv.org/html/2509.02896v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-92c7cd3291ab", "catalogIds": ["ref-92c7cd3291ab"], "title": "KEN: An Execution Engine for Unstructured Database Systems", "kind": "paper", "scope": "related", "date": "2026", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://www.vldb.org/pvldb/vol19/p902-kossmann.pdf", "metadataSource": "https://www.vldb.org/pvldb/vol19/p902-kossmann.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "Ferdi Kossmann", "affiliations": ["MIT"], "personId": "ferdi-kossmann" }, { "name": "Ziniu Wu", "affiliations": ["MIT"], "personId": "ziniu-wu" }, { "name": "Alex Turk", "affiliations": ["Intel Labs"], "personId": "alex-turk" }, { "name": "Nesime Tatbul", "affiliations": ["MIT", "Intel Labs"], "personId": "nesime-tatbul" }, { "name": "Lei Cao", "affiliations": ["University of Arizona"], "personId": "lei-cao" }, { "name": "Samuel Madden", "affiliations": ["MIT"], "personId": "samuel-madden" } ], "affiliationSource": "https://www.vldb.org/pvldb/vol19/p902-kossmann.pdf" }, { "id": "arxiv-2508-05012", "catalogIds": ["arxiv-2508-05012"], "title": "Making Prompts First-Class Citizens for Adaptive LLM Pipelines", "kind": "paper", "scope": "related", "date": "2025-08-07", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2508.05012v2", "metadataSource": "https://arxiv.org/abs/2508.05012", "checkedDate": "2026-10-25", "authors": [ { "name": "Ugur Cetintemel", "affiliations": ["Brown University"], "personId": "ugur-cetintemel" }, { "name": "Shu Chen", "affiliations": ["Brown University"], "personId": "shu-chen" }, { "name": "Alexander W. Lee", "affiliations": ["Brown University"], "personId": "alexander-w-lee" }, { "name": "Deepti Raghavan", "affiliations": ["Brown University"], "personId": "deepti-raghavan" }, { "name": "Duo Lu", "affiliations": ["Brown University"], "personId": "duo-lu" }, { "name": "Andrew Crotty", "affiliations": ["Northwestern University"], "personId": "andrew-crotty" } ], "affiliationSource": "https://arxiv.org/html/2508.05012v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2604-00660", "catalogIds": ["arxiv-2604-00660"], "title": "Streaming Model Cascades for Semantic SQL", "kind": "paper", "scope": "related", "date": "2026-04-01", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2604.00660v2", "metadataSource": "https://arxiv.org/abs/2604.00660", "checkedDate": "2026-10-25", "authors": [ { "name": "Paweł Liskowski", "affiliations": ["Snowflake"], "personId": "pawel-liskowski" }, { "name": "Kyle Schmaus", "affiliations": ["Snowflake"], "personId": "kyle-schmaus" } ], "affiliationSource": "https://arxiv.org/html/2604.00660v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2402-17882", "catalogIds": ["arxiv-2402-17882"], "title": "BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra", "kind": "paper", "scope": "related", "date": "2024-02-27", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2402.17882v2", "metadataSource": "https://arxiv.org/abs/2402.17882", "checkedDate": "2026-10-25", "authors": [ { "name": "Parker Glenn", "affiliations": ["Fidelity Investments"], "personId": "parker-glenn" }, { "name": "Parag Pravin Dakle", "affiliations": ["Fidelity Investments"], "personId": "parag-pravin-dakle" }, { "name": "Liang Wang", "affiliations": ["Fidelity Investments"], "personId": "liang-wang" }, { "name": "Preethi Raghavan", "affiliations": ["Fidelity Investments"], "personId": "preethi-raghavan" } ], "affiliationSource": "https://arxiv.org/html/2402.17882v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2408-00884", "catalogIds": ["arxiv-2408-00884"], "title": "Hybrid Querying Over Relational Databases and Large Language Models", "kind": "paper", "scope": "related", "date": "2024-08-01", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/2408.00884v2", "metadataSource": "https://arxiv.org/abs/2408.00884", "checkedDate": "2026-10-25", "authors": [ { "name": "Fuheng Zhao", "affiliations": ["UC Santa Barbara"], "personId": "fuheng-zhao" }, { "name": "Divyakant Agrawal", "affiliations": ["UC Santa Barbara"], "personId": "divyakant-agrawal" }, { "name": "Amr El Abbadi", "affiliations": ["UC Santa Barbara"], "personId": "amr-el-abbadi" } ], "affiliationSource": "https://arxiv.org/html/2408.00884v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-efdd20df7d0b", "catalogIds": ["ref-efdd20df7d0b"], "title": "Logical and Physical Optimizations for SQL Query Execution over Large Language Models", "kind": "paper", "scope": "related", "date": "2025-06-17", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://doi.org/10.1145/3725411", "metadataSource": "https://api.crossref.org/works/10.1145%2F3725411", "checkedDate": "2026-10-25", "authors": [ { "name": "Dario Satriani", "affiliations": ["University of Basilicata, Potenza, Italy"], "personId": "dario-satriani" }, { "name": "Enzo Veltri", "affiliations": ["University of Basilicata, Potenza, Italy"], "personId": "enzo-veltri" }, { "name": "Donatello Santoro", "affiliations": ["University of Basilicata, Potenza, Italy"], "personId": "donatello-santoro" }, { "name": "Sara Rosato", "affiliations": ["EURECOM, Biot, France"], "personId": "sara-rosato" }, { "name": "Simone Varriale", "affiliations": ["EURECOM, Biot, France"], "personId": "simone-varriale" }, { "name": "Paolo Papotti", "affiliations": ["EURECOM, Biot, France"], "personId": "paolo-papotti" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F3725411" }, { "id": "ref-d845a48dcc81", "catalogIds": ["ref-d845a48dcc81"], "title": "ThalamusDB: Approximate Query Processing on Multi-Modal Data", "kind": "paper", "scope": "related", "date": "2024-05-29", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://api.crossref.org/works/10.1145%2F3654989", "metadataSource": "https://api.crossref.org/works/10.1145%2F3654989", "checkedDate": "2026-10-25", "authors": [ { "name": "Saehan Jo", "affiliations": ["Cornell University, Ithaca, NY, USA"], "personId": "saehan-jo" }, { "name": "Immanuel Trummer", "affiliations": ["Cornell University, Ithaca, NY, USA"], "personId": "immanuel-trummer" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F3654989" }, { "id": "ref-c1f091aed610", "catalogIds": ["ref-c1f091aed610"], "title": "Approximate Selection with Guarantees using Proxies", "kind": "paper", "scope": "related", "date": "2020", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://www.vldb.org/pvldb/vol13/p1990-kang.pdf", "metadataSource": "https://www.vldb.org/pvldb/vol13/p1990-kang.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "Daniel Kang", "affiliations": ["Stanford University"], "personId": "daniel-kang" }, { "name": "Edward Gan", "affiliations": ["Stanford University"], "personId": "edward-gan" }, { "name": "Peter Bailis", "affiliations": ["Stanford University"], "personId": "peter-bailis" }, { "name": "Tatsunori Hashimoto", "affiliations": ["Stanford University"], "personId": "tatsunori-hashimoto" }, { "name": "Matei Zaharia", "affiliations": ["Stanford University"], "personId": "matei-zaharia" } ], "affiliationSource": "https://www.vldb.org/pvldb/vol13/p1990-kang.pdf" }, { "id": "ref-120601be24c4", "catalogIds": ["ref-120601be24c4"], "title": "Accelerating Approximate Aggregation Queries with Expensive Predicates", "kind": "paper", "scope": "related", "date": "2021", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://www.vldb.org/pvldb/vol14/p2341-kang.pdf", "metadataSource": "https://www.vldb.org/pvldb/vol14/p2341-kang.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "Daniel Kang", "affiliations": ["Stanford University"], "personId": "daniel-kang" }, { "name": "John Guibas", "affiliations": ["Stanford University"], "personId": "john-guibas" }, { "name": "Peter Bailis", "affiliations": ["Stanford University"], "personId": "peter-bailis" }, { "name": "Tatsunori Hashimoto", "affiliations": ["Stanford University"], "personId": "tatsunori-hashimoto" }, { "name": "Yi Sun", "affiliations": ["University of Chicago"], "personId": "yi-sun" }, { "name": "Matei Zaharia", "affiliations": ["Stanford University"], "personId": "matei-zaharia" } ], "affiliationSource": "https://www.vldb.org/pvldb/vol14/p2341-kang.pdf" }, { "id": "ref-c6cf5f1702f9", "catalogIds": ["ref-c6cf5f1702f9"], "title": "Accelerating Machine Learning Inference with Probabilistic Predicates", "kind": "paper", "scope": "related", "date": "2018-05-27", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://doi.org/10.1145/3183713.3183751", "metadataSource": "https://api.crossref.org/works/10.1145%2F3183713.3183751", "checkedDate": "2026-10-25", "authors": [ { "name": "Yao Lu", "affiliations": ["Microsoft &University of Washington, Redmond, WA, USA"], "personId": "yao-lu" }, { "name": "Aakanksha Chowdhery", "affiliations": ["Princeton University &Microsoft, Princeton, NJ, USA"], "personId": "aakanksha-chowdhery" }, { "name": "Srikanth Kandula", "affiliations": ["Microsoft, Redmond, WA, USA"], "personId": "srikanth-kandula" }, { "name": "Surajit Chaudhuri", "affiliations": ["Microsoft, Redmond, WA, USA"], "personId": "surajit-chaudhuri" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F3183713.3183751" }, { "id": "ref-564f2022e48d", "catalogIds": ["ref-564f2022e48d"], "title": "Wander Join: Online Aggregation via Random Walks", "kind": "paper", "scope": "related", "date": "2016-06-14", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://doi.org/10.1145/2882903.2915235", "metadataSource": "https://api.crossref.org/works/10.1145%2F2882903.2915235", "checkedDate": "2026-10-25", "authors": [ { "name": "Feifei Li", "affiliations": ["University of Utah, Salt Lake City, USA"], "personId": "feifei-li" }, { "name": "Bin Wu", "affiliations": ["Hong Kong University of Science and Technology, Hong Kong, China"], "personId": "bin-wu" }, { "name": "Ke Yi", "affiliations": ["Hong Kong University of Science and Technology, Hong Kong, China"], "personId": "ke-yi" }, { "name": "Zhuoyue Zhao", "affiliations": ["Shanghai Jiao Tong University, Shanghai, China"], "personId": "zhuoyue-zhao" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F2882903.2915235" }, { "id": "ref-37c0c1fa8efa", "catalogIds": ["ref-37c0c1fa8efa"], "title": "Eddies: continuously adaptive query processing", "kind": "paper", "scope": "related", "date": "2000-05-16", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://doi.org/10.1145/342009.335420", "metadataSource": "https://api.crossref.org/works/10.1145%2F342009.335420", "checkedDate": "2026-10-25", "authors": [ { "name": "Ron Avnur", "affiliations": ["University of California, Berkeley"], "personId": "ron-avnur" }, { "name": "Joseph M. Hellerstein", "affiliations": ["University of California, Berkeley"], "personId": "joseph-m-hellerstein" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F342009.335420" }, { "id": "ref-f7ee7814e14e", "catalogIds": ["ref-f7ee7814e14e"], "title": "BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics", "kind": "paper", "scope": "related", "date": "2018-05-02", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://arxiv.org/abs/1805.01046v2", "metadataSource": "https://arxiv.org/abs/1805.01046", "checkedDate": "2026-10-25", "authors": [ { "name": "Daniel Kang", "affiliations": ["Stanford University"], "personId": "daniel-kang" }, { "name": "Peter Bailis", "affiliations": ["Stanford University"], "personId": "peter-bailis" }, { "name": "Matei Zaharia", "affiliations": ["Stanford University"], "personId": "matei-zaharia" } ], "affiliationSource": "https://arxiv.org/html/1805.01046v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-8891df20ddbe", "catalogIds": ["ref-8891df20ddbe"], "title": "NoScope: Optimizing Neural Network Queries over Video at Scale", "kind": "paper", "scope": "related", "date": "2017", "topic": "Operator-specific optimizer and query-centric workflow papers", "url": "https://www.vldb.org/pvldb/vol10/p1586-kang.pdf", "metadataSource": "https://www.vldb.org/pvldb/vol10/p1586-kang.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "Daniel Kang", "affiliations": ["Stanford University"], "personId": "daniel-kang" }, { "name": "John Emmons", "affiliations": ["Stanford University"], "personId": "john-emmons" }, { "name": "Firas Abuzaid", "affiliations": ["Stanford University"], "personId": "firas-abuzaid" }, { "name": "Peter Bailis", "affiliations": ["Stanford University"], "personId": "peter-bailis" }, { "name": "Matei Zaharia", "affiliations": ["Stanford University"], "personId": "matei-zaharia" } ], "affiliationSource": "https://www.vldb.org/pvldb/vol10/p1586-kang.pdf" }, { "id": "arxiv-2409-00847", "catalogIds": ["arxiv-2409-00847"], "title": "The Design of an LLM-powered Unstructured Analytics System", "kind": "paper", "scope": "related", "date": "2024-09-01", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2409.00847v3", "metadataSource": "https://arxiv.org/abs/2409.00847", "checkedDate": "2026-10-25", "authors": [ { "name": "Eric Anderson", "affiliations": ["Aryn"], "personId": "eric-anderson" }, { "name": "Jonathan Fritz", "affiliations": ["Aryn"], "personId": "jonathan-fritz" }, { "name": "Austin Lee", "affiliations": ["Aryn"], "personId": "austin-lee" }, { "name": "Bohou Li", "affiliations": ["Aryn"], "personId": "bohou-li" }, { "name": "Mark Lindblad", "affiliations": ["Aryn"], "personId": "mark-lindblad" }, { "name": "Henry Lindeman", "affiliations": ["Aryn"], "personId": "henry-lindeman" }, { "name": "Alex Meyer", "affiliations": ["Aryn"], "personId": "alex-meyer" }, { "name": "Parth Parmar", "affiliations": ["Aryn"], "personId": "parth-parmar" }, { "name": "Tanvi Ranade", "affiliations": ["Aryn"], "personId": "tanvi-ranade" }, { "name": "Mehul A. Shah", "affiliations": ["Aryn"], "personId": "mehul-a-shah" }, { "name": "Benjamin Sowell", "affiliations": ["Aryn"], "personId": "benjamin-sowell" }, { "name": "Dan Tecuci", "affiliations": ["Aryn"], "personId": "dan-tecuci" }, { "name": "Vinayak Thapliyal", "affiliations": ["Aryn"], "personId": "vinayak-thapliyal" }, { "name": "Matt Welsh", "affiliations": ["Aryn"], "personId": "matt-welsh" } ], "affiliationSource": "https://arxiv.org/html/2409.00847v3", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-f9e3f7194e66", "catalogIds": ["ref-f9e3f7194e66"], "title": "Apache Arrow DataFusion: A Fast, Embeddable, Modular Analytic Query Engine", "kind": "paper", "scope": "related", "date": "2024-06-09", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://doi.org/10.1145/3626246.3653368", "metadataSource": "https://api.crossref.org/works/10.1145%2F3626246.3653368", "checkedDate": "2026-10-25", "authors": [ { "name": "Andrew Lamb", "affiliations": ["InfluxData, Boston, MA, USA"], "personId": "andrew-lamb" }, { "name": "Yijie Shen", "affiliations": ["Space and Time, Irvine, CA, USA"], "personId": "yijie-shen" }, { "name": "Daniël Heres", "affiliations": ["Coralogix, Utrecht, Netherlands"], "personId": "daniel-heres" }, { "name": "Jayjeet Chakraborty", "affiliations": ["UC Santa Cruz, Santa Cruz, CA, USA"], "personId": "jayjeet-chakraborty" }, { "name": "Mehmet Ozan Kabak", "affiliations": ["Synnada, Austin, TX, USA"], "personId": "mehmet-ozan-kabak" }, { "name": "Liang-Chi Hsieh", "affiliations": ["Apple, Seattle, WA, USA"], "personId": "liang-chi-hsieh" }, { "name": "Chao Sun", "affiliations": ["Apple, Cupertino, CA, USA"], "personId": "chao-sun" } ], "affiliationSource": "https://api.crossref.org/works/10.1145%2F3626246.3653368" }, { "id": "arxiv-2609-19491", "catalogIds": ["arxiv-2609-19491"], "title": "Efficiently Linking Unstructured Data for Multi-step Reasoning", "kind": "paper", "scope": "related", "date": "2026-09-16", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2609.19491v1", "metadataSource": "https://arxiv.org/abs/2609.19491", "checkedDate": "2026-10-25", "authors": [ { "name": "Jiaming Liang", "affiliations": ["University of Pennsylvania"], "personId": "jiaming-liang" }, { "name": "Haydn Jones", "affiliations": ["University of Pennsylvania"], "personId": "haydn-jones" }, { "name": "Jacob R. Gardner", "affiliations": ["University of Pennsylvania"], "personId": "jacob-r-gardner" }, { "name": "Mark Yatskar", "affiliations": ["University of Pennsylvania"], "personId": "mark-yatskar" }, { "name": "Zachary Ives", "affiliations": ["University of Pennsylvania"], "personId": "zachary-ives" } ], "affiliationSource": "https://arxiv.org/html/2609.19491v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2609-09002", "catalogIds": ["arxiv-2609-09002"], "title": "Factorized and Vectorized Execution: Optimizing Analytical and Semantic Queries over Relations", "kind": "paper", "scope": "related", "date": "2026-09-08", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2609.09002v1", "metadataSource": "https://arxiv.org/abs/2609.09002", "checkedDate": "2026-10-25", "authors": [ { "name": "Sunny Yasser", "affiliations": ["Polytechnique Montréal"], "personId": "sunny-yasser" }, { "name": "Anas Dorbani", "affiliations": ["Polytechnique Montréal"], "personId": "anas-dorbani" }, { "name": "Amine Mhedhbi", "affiliations": ["Polytechnique Montréal"], "personId": "amine-mhedhbi" } ], "affiliationSource": "https://arxiv.org/html/2609.09002v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2309-06180", "catalogIds": ["arxiv-2309-06180"], "title": "Efficient Memory Management for Large Language Model Serving with PagedAttention", "kind": "paper", "scope": "related", "date": "2023-09-12", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2309.06180v1", "metadataSource": "https://arxiv.org/abs/2309.06180", "checkedDate": "2026-10-25", "authors": [ { "name": "Woosuk Kwon", "affiliations": ["UC Berkeley"], "personId": "woosuk-kwon" }, { "name": "Zhuohan Li", "affiliations": ["UC Berkeley"], "personId": "zhuohan-li" }, { "name": "Siyuan Zhuang", "affiliations": ["UC Berkeley"], "personId": "siyuan-zhuang" }, { "name": "Ying Sheng", "affiliations": ["UC Berkeley", "Stanford University"], "personId": "ying-sheng" }, { "name": "Lianmin Zheng", "affiliations": ["UC Berkeley"], "personId": "lianmin-zheng" }, { "name": "Cody Hao Yu", "affiliations": ["Independent researcher"], "personId": "cody-hao-yu" }, { "name": "Joseph E. Gonzalez", "affiliations": ["UC Berkeley"], "personId": "joseph-e-gonzalez" }, { "name": "Hao Zhang", "affiliations": ["UC San Diego"], "personId": "hao-zhang-ucsd" }, { "name": "Ion Stoica", "affiliations": ["UC Berkeley"], "personId": "ion-stoica" } ], "affiliationSource": "https://arxiv.org/html/2309.06180v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2312-07104", "catalogIds": ["arxiv-2312-07104"], "title": "SGLang: Efficient Execution of Structured Language Model Programs", "kind": "paper", "scope": "related", "date": "2023-12-12", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2312.07104v2", "metadataSource": "https://arxiv.org/abs/2312.07104", "checkedDate": "2026-10-25", "authors": [ { "name": "Lianmin Zheng", "affiliations": ["UC Berkeley"], "personId": "lianmin-zheng" }, { "name": "Liangsheng Yin", "affiliations": ["Shanghai Jiao Tong University"], "personId": "liangsheng-yin" }, { "name": "Zhiqiang Xie", "affiliations": ["Stanford University"], "personId": "zhiqiang-xie" }, { "name": "Chuyue Sun", "affiliations": ["Stanford University"], "personId": "chuyue-sun" }, { "name": "Jeff Huang", "affiliations": ["Texas A&M University"], "personId": "jeff-huang" }, { "name": "Cody Hao Yu", "affiliations": ["Independent researcher"], "personId": "cody-hao-yu" }, { "name": "Shiyi Cao", "affiliations": ["UC Berkeley"], "personId": "shiyi-cao" }, { "name": "Christos Kozyrakis", "affiliations": ["Stanford University"], "personId": "christos-kozyrakis" }, { "name": "Ion Stoica", "affiliations": ["UC Berkeley"], "personId": "ion-stoica" }, { "name": "Joseph E. Gonzalez", "affiliations": ["UC Berkeley"], "personId": "joseph-e-gonzalez" }, { "name": "Clark Barrett", "affiliations": ["Stanford University"], "personId": "clark-barrett" }, { "name": "Ying Sheng", "affiliations": ["Stanford University"], "personId": "ying-sheng" } ], "affiliationSource": "https://arxiv.org/pdf/2312.07104v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-76210079970f", "catalogIds": ["ref-76210079970f"], "title": "Orca: A Distributed Serving System for Transformer-Based Generative Models", "kind": "paper", "scope": "related", "date": "2022", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://www.usenix.org/conference/osdi22/presentation/yu", "metadataSource": "https://www.usenix.org/conference/osdi22/presentation/yu", "checkedDate": "2026-10-25", "authors": [ { "name": "Gyeong-In Yu", "affiliations": ["Seoul National University"], "personId": "gyeong-in-yu" }, { "name": "Joo Seong Jeong", "affiliations": ["Seoul National University"], "personId": "joo-seong-jeong" }, { "name": "Geon-Woo Kim", "affiliations": ["FriendliAI and Seoul National University"], "personId": "geon-woo-kim" }, { "name": "Soojeong Kim", "affiliations": ["FriendliAI"], "personId": "soojeong-kim" }, { "name": "Byung-Gon Chun", "affiliations": ["FriendliAI and Seoul National University"], "personId": "byung-gon-chun" } ], "affiliationSource": "https://www.usenix.org/conference/osdi22/presentation/yu" }, { "id": "ref-bf0630162d5d", "catalogIds": ["ref-bf0630162d5d"], "title": "Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve", "kind": "paper", "scope": "related", "date": "2024", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://www.usenix.org/conference/osdi24/presentation/agrawal", "metadataSource": "https://www.usenix.org/conference/osdi24/presentation/agrawal", "checkedDate": "2026-10-25", "authors": [ { "name": "Amey Agrawal", "affiliations": ["Georgia Institute of Technology"], "personId": "amey-agrawal" }, { "name": "Nitin Kedia", "affiliations": ["Microsoft Research India"], "personId": "nitin-kedia" }, { "name": "Ashish Panwar", "affiliations": ["Microsoft Research India"], "personId": "ashish-panwar" }, { "name": "Jayashree Mohan", "affiliations": ["Microsoft Research India"], "personId": "jayashree-mohan" }, { "name": "Nipun Kwatra", "affiliations": ["Microsoft Research India"], "personId": "nipun-kwatra" }, { "name": "Bhargav Gulavani", "affiliations": ["Microsoft Research India"], "personId": "bhargav-gulavani" }, { "name": "Alexey Tumanov", "affiliations": ["Georgia Institute of Technology"], "personId": "alexey-tumanov" }, { "name": "Ramachandran Ramjee", "affiliations": ["Microsoft Research India"], "personId": "ramachandran-ramjee" } ], "affiliationSource": "https://www.usenix.org/conference/osdi24/presentation/agrawal" }, { "id": "ref-d08d91468182", "catalogIds": ["ref-d08d91468182"], "title": "DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving", "kind": "paper", "scope": "related", "date": "2024", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://www.usenix.org/conference/osdi24/presentation/zhong-yinmin", "metadataSource": "https://www.usenix.org/conference/osdi24/presentation/zhong-yinmin", "checkedDate": "2026-10-25", "authors": [ { "name": "Yinmin Zhong", "affiliations": ["Peking University"], "personId": "yinmin-zhong" }, { "name": "Shengyu Liu", "affiliations": ["Peking University"], "personId": "shengyu-liu" }, { "name": "Junda Chen", "affiliations": ["UC San Diego"], "personId": "junda-chen" }, { "name": "Jianbo Hu", "affiliations": ["Peking University"], "personId": "jianbo-hu" }, { "name": "Yibo Zhu", "affiliations": ["StepFun"], "personId": "yibo-zhu" }, { "name": "Xuanzhe Liu", "affiliations": ["School of Computer Science, Peking University"], "personId": "xuanzhe-liu" }, { "name": "Xin Jin", "affiliations": ["School of Computer Science, Peking University"], "personId": "xin-jin" }, { "name": "Hao Zhang", "affiliations": ["UC San Diego"], "personId": "hao-zhang-ucsd" } ], "affiliationSource": "https://www.usenix.org/conference/osdi24/presentation/zhong-yinmin" }, { "id": "ref-4a9db4de3b2b", "catalogIds": ["ref-4a9db4de3b2b"], "title": "Llumnix: Dynamic Scheduling for Large Language Model Serving", "kind": "paper", "scope": "related", "date": "2024", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://www.usenix.org/conference/osdi24/presentation/sun-biao", "metadataSource": "https://www.usenix.org/conference/osdi24/presentation/sun-biao", "checkedDate": "2026-10-25", "authors": [ { "name": "Biao Sun", "affiliations": ["Alibaba Group"], "personId": "biao-sun" }, { "name": "Ziming Huang", "affiliations": ["Alibaba Group"], "personId": "ziming-huang" }, { "name": "Hanyu Zhao", "affiliations": ["Alibaba Group"], "personId": "hanyu-zhao" }, { "name": "Wencong Xiao", "affiliations": ["Alibaba Group"], "personId": "wencong-xiao" }, { "name": "Xinyi Zhang", "affiliations": ["Alibaba Group"], "personId": "xinyi-zhang" }, { "name": "Yong Li", "affiliations": ["Alibaba Group"], "personId": "yong-li" }, { "name": "Wei Lin", "affiliations": ["Alibaba Group"], "personId": "wei-lin" } ], "affiliationSource": "https://www.usenix.org/conference/osdi24/presentation/sun-biao" }, { "id": "ref-c2e55193e68a", "catalogIds": ["ref-c2e55193e68a"], "title": "Prompt Cache: Modular Attention Reuse for Low-Latency Inference", "kind": "paper", "scope": "related", "date": "2023-11-07", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2311.04934v2", "metadataSource": "https://arxiv.org/abs/2311.04934", "checkedDate": "2026-10-25", "authors": [ { "name": "In Gim", "affiliations": ["Yale University"], "personId": "in-gim" }, { "name": "Guojun Chen", "affiliations": ["Yale University"], "personId": "guojun-chen" }, { "name": "Seung-seob Lee", "affiliations": ["Yale University"], "personId": "seung-seob-lee" }, { "name": "Nikhil Sarda", "affiliations": ["Google"], "personId": "nikhil-sarda" }, { "name": "Anurag Khandelwal", "affiliations": ["Yale University"], "personId": "anurag-khandelwal" }, { "name": "Lin Zhong", "affiliations": ["Yale University"], "personId": "lin-zhong" } ], "affiliationSource": "https://arxiv.org/pdf/2311.04934v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2512-03389", "catalogIds": ["arxiv-2512-03389"], "title": "Continuous Prompts: LLM-Augmented Pipeline Processing over Unstructured Streams", "kind": "paper", "scope": "related", "date": "2025-12-03", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2512.03389v1", "metadataSource": "https://arxiv.org/abs/2512.03389", "checkedDate": "2026-10-25", "authors": [ { "name": "Shu Chen", "affiliations": ["Brown University"], "personId": "shu-chen" }, { "name": "Deepti Raghavan", "affiliations": ["Brown University"], "personId": "deepti-raghavan" }, { "name": "Uğur Çetintemel", "affiliations": ["Brown University"], "personId": "ugur-cetintemel" } ], "affiliationSource": "https://arxiv.org/html/2512.03389v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2602-05134", "catalogIds": ["arxiv-2602-05134"], "title": "SemPipes -- Optimizable Semantic Data Operators for Tabular Machine Learning Pipelines", "kind": "paper", "scope": "related", "date": "2026-02-04", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2602.05134v1", "metadataSource": "https://arxiv.org/abs/2602.05134", "checkedDate": "2026-10-25", "authors": [ { "name": "Olga Ovcharenko", "affiliations": ["BIFOLD", "TU Berlin"], "personId": "olga-ovcharenko" }, { "name": "Matthias Boehm", "affiliations": ["BIFOLD", "TU Berlin"], "personId": "matthias-boehm" }, { "name": "Sebastian Schelter", "affiliations": ["BIFOLD", "TU Berlin"], "personId": "sebastian-schelter" } ], "affiliationSource": "https://arxiv.org/html/2602.05134v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2601-05536", "catalogIds": ["arxiv-2601-05536"], "title": "Task Cascades for Efficient Unstructured Data Processing", "kind": "paper", "scope": "related", "date": "2026-01-09", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2601.05536v1", "metadataSource": "https://arxiv.org/abs/2601.05536", "checkedDate": "2026-10-25", "authors": [ { "name": "Shreya Shankar", "affiliations": ["UC Berkeley"], "personId": "shreya-shankar" }, { "name": "Sepanta Zeighami", "affiliations": ["UC Berkeley"], "personId": "sepanta-zeighami" }, { "name": "Aditya Parameswaran", "affiliations": ["UC Berkeley"], "personId": "aditya-g-parameswaran" } ], "affiliationSource": "https://arxiv.org/html/2601.05536v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2509-02751", "catalogIds": ["arxiv-2509-02751"], "title": "Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics", "kind": "paper", "scope": "related", "date": "2025-09-02", "topic": "Serving-layer, runtime, and adjacent pipeline systems", "url": "https://arxiv.org/abs/2509.02751v1", "metadataSource": "https://arxiv.org/abs/2509.02751", "checkedDate": "2026-10-25", "authors": [ { "name": "Matthew Russo", "affiliations": ["MIT"], "personId": "matthew-russo" }, { "name": "Tim Kraska", "affiliations": ["MIT"], "personId": "tim-kraska" } ], "affiliationSource": "https://arxiv.org/html/2509.02751v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2408-14717", "catalogIds": ["arxiv-2408-14717"], "title": "Text2SQL is Not Enough: Unifying AI and Databases with TAG", "kind": "paper", "scope": "related", "date": "2024-08-27", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2408.14717v1", "metadataSource": "https://arxiv.org/abs/2408.14717", "checkedDate": "2026-10-25", "authors": [ { "name": "Asim Biswal", "affiliations": ["UC Berkeley"], "personId": "asim-biswal" }, { "name": "Liana Patel", "affiliations": ["Stanford University"], "personId": "liana-patel" }, { "name": "Siddarth Jha", "affiliations": ["UC Berkeley"], "personId": "siddarth-jha" }, { "name": "Amog Kamsetty", "affiliations": ["UC Berkeley"], "personId": "amog-kamsetty" }, { "name": "Shu Liu", "affiliations": ["UC Berkeley"], "personId": "shu-liu" }, { "name": "Joseph E. Gonzalez", "affiliations": ["UC Berkeley"], "personId": "joseph-e-gonzalez" }, { "name": "Carlos Guestrin", "affiliations": ["Stanford University"], "personId": "carlos-guestrin" }, { "name": "Matei Zaharia", "affiliations": ["UC Berkeley"], "personId": "matei-zaharia" } ], "affiliationSource": "https://arxiv.org/html/2408.14717v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2307-07306", "catalogIds": ["arxiv-2307-07306"], "title": "C3: Zero-shot Text-to-SQL with ChatGPT", "kind": "paper", "scope": "related", "date": "2023-07-14", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2307.07306v1", "metadataSource": "https://arxiv.org/abs/2307.07306", "checkedDate": "2026-10-25", "authors": [ { "name": "Xuemei Dong", "affiliations": ["Zhejiang University"], "personId": "xuemei-dong" }, { "name": "Chao Zhang", "affiliations": ["Zhejiang University"], "personId": "chao-zhang" }, { "name": "Yuhang Ge", "affiliations": ["Zhejiang University"], "personId": "yuhang-ge" }, { "name": "Yuren Mao", "affiliations": ["Zhejiang University"], "personId": "yuren-mao" }, { "name": "Yunjun Gao", "affiliations": ["Zhejiang University"], "personId": "yunjun-gao" }, { "name": "lu Chen", "affiliations": ["Zhejiang University"], "personId": "lu-chen" }, { "name": "Jinshu Lin", "affiliations": ["Hundsun Technologies"], "personId": "jinshu-lin" }, { "name": "Dongfang Lou", "affiliations": ["Hundsun Technologies"], "personId": "dongfang-lou" } ], "affiliationSource": "https://arxiv.org/html/2307.07306v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-c289f402557f", "catalogIds": ["ref-c289f402557f"], "title": "In-depth Analysis of LLM-Based Schema Linking", "kind": "paper", "scope": "related", "date": "2026-03-24", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://www.openproceedings.org/2026/conf/edbt/paper-24.pdf", "metadataSource": "https://www.openproceedings.org/2026/conf/edbt/paper-24.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "George Katsogiannis-Meimarakis", "affiliations": ["IBM Research", "Université Grenoble Alpes", "Athena Research Center"], "personId": "george-katsogiannis-meimarakis" }, { "name": "Katsiaryna Mirylenka", "affiliations": ["IBM Research"], "personId": "katsiaryna-mirylenka" }, { "name": "Paolo Scotton", "affiliations": ["IBM Research"], "personId": "paolo-scotton" }, { "name": "Francesco Fusco", "affiliations": ["IBM Research"], "personId": "francesco-fusco" }, { "name": "Abdel Labbi", "affiliations": ["IBM Research"], "personId": "abdel-labbi" } ], "affiliationSource": "https://www.openproceedings.org/2026/conf/edbt/paper-24.pdf" }, { "id": "arxiv-2205-09911", "catalogIds": ["arxiv-2205-09911"], "title": "Can Foundation Models Wrangle Your Data?", "kind": "paper", "scope": "related", "date": "2022-05-20", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2205.09911v2", "metadataSource": "https://arxiv.org/abs/2205.09911", "checkedDate": "2026-10-25", "authors": [ { "name": "Avanika Narayan", "affiliations": ["Stanford University"], "personId": "avanika-narayan" }, { "name": "Ines Chami", "affiliations": ["Numbers Station"], "personId": "ines-chami" }, { "name": "Laurel Orr", "affiliations": ["Stanford University"], "personId": "laurel-orr" }, { "name": "Simran Arora", "affiliations": ["Stanford University"], "personId": "simran-arora" }, { "name": "Christopher Ré", "affiliations": ["Stanford University"], "personId": "christopher-re" } ], "affiliationSource": "https://arxiv.org/html/2205.09911v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-547df79ea94f", "catalogIds": ["ref-547df79ea94f"], "title": "BoostER: Leveraging Large Language Models for Enhancing Entity Resolution", "kind": "paper", "scope": "related", "date": "2024-03-11", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2403.06434v1", "metadataSource": "https://arxiv.org/abs/2403.06434", "checkedDate": "2026-10-25", "authors": [ { "name": "Huahang Li", "affiliations": ["Hong Kong Polytechnic University"], "personId": "huahang-li" }, { "name": "Shuangyin Li", "affiliations": ["South China Normal University"], "personId": "shuangyin-li" }, { "name": "Fei Hao", "affiliations": ["Hong Kong Polytechnic University"], "personId": "fei-hao" }, { "name": "Chen Jason Zhang", "affiliations": ["Hong Kong Polytechnic University"], "personId": "chen-jason-zhang" }, { "name": "Yuanfeng Song", "affiliations": ["WeBank"], "personId": "yuanfeng-song" }, { "name": "Lei Chen", "affiliations": ["Hong Kong University of Science and Technology"], "personId": "lei-chen" } ], "affiliationSource": "https://arxiv.org/html/2403.06434v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-58178413b245", "catalogIds": ["ref-58178413b245"], "title": "Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching", "kind": "paper", "scope": "related", "date": "2024-05-27", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2405.16884v3", "metadataSource": "https://arxiv.org/abs/2405.16884", "checkedDate": "2026-10-25", "authors": [ { "name": "Tianshu Wang", "affiliations": [ "Chinese Academy of Sciences", "University of Chinese Academy of Sciences" ], "personId": "tianshu-wang" }, { "name": "Xiaoyang Chen", "affiliations": ["University of Chinese Academy of Sciences"], "personId": "xiaoyang-chen" }, { "name": "Hongyu Lin", "affiliations": ["Chinese Academy of Sciences"], "personId": "hongyu-lin" }, { "name": "Xuanang Chen", "affiliations": ["Chinese Academy of Sciences"], "personId": "xuanang-chen" }, { "name": "Xianpei Han", "affiliations": ["Chinese Academy of Sciences"], "personId": "xianpei-han" }, { "name": "Hao Wang", "affiliations": ["Alibaba Group"], "personId": "hao-wang" }, { "name": "Zhenyu Zeng", "affiliations": ["Alibaba Group"], "personId": "zhenyu-zeng" }, { "name": "Le Sun", "affiliations": ["Chinese Academy of Sciences"], "personId": "le-sun" } ], "affiliationSource": "https://arxiv.org/pdf/2405.16884v3", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-eded7ed7ba25", "catalogIds": ["ref-eded7ed7ba25"], "title": "Entity Matching using Large Language Models", "kind": "paper", "scope": "related", "date": "2023-10-17", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2310.11244v4", "metadataSource": "https://arxiv.org/abs/2310.11244", "checkedDate": "2026-10-25", "authors": [ { "name": "Ralph Peeters", "affiliations": ["University of Mannheim"], "personId": "ralph-peeters" }, { "name": "Aaron Steiner", "affiliations": ["University of Mannheim"], "personId": "aaron-steiner" }, { "name": "Christian Bizer", "affiliations": ["University of Mannheim"], "personId": "christian-bizer" } ], "affiliationSource": "https://arxiv.org/html/2310.11244v4", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-c2f9278dc837", "catalogIds": ["ref-c2f9278dc837"], "title": "Fine-tuning Large Language Models for Entity Matching", "kind": "paper", "scope": "related", "date": "2024-09-12", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2409.08185v2", "metadataSource": "https://arxiv.org/abs/2409.08185", "checkedDate": "2026-10-25", "authors": [ { "name": "Aaron Steiner", "affiliations": ["University of Mannheim"], "personId": "aaron-steiner" }, { "name": "Ralph Peeters", "affiliations": ["University of Mannheim"], "personId": "ralph-peeters" }, { "name": "Christian Bizer", "affiliations": ["University of Mannheim"], "personId": "christian-bizer" } ], "affiliationSource": "https://arxiv.org/html/2409.08185v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-59c3b3b8d8eb", "catalogIds": ["ref-59c3b3b8d8eb"], "title": "UniDM: A Unified Framework for Data Manipulation with Large Language Models", "kind": "paper", "scope": "related", "date": "2024-05-10", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2405.06510v1", "metadataSource": "https://arxiv.org/abs/2405.06510v1", "checkedDate": "2026-10-25", "authors": [ { "name": "Yichen Qian", "affiliations": ["Alibaba Group"], "personId": "yichen-qian" }, { "name": "Yongyi He", "affiliations": ["Alibaba Group", "University of Science and Technology of China"], "personId": "yongyi-he" }, { "name": "Rong Zhu", "affiliations": ["Alibaba Group"], "personId": "rong-zhu" }, { "name": "Jintao Huang", "affiliations": ["Alibaba Group", "University of Science and Technology of China"], "personId": "jintao-huang" }, { "name": "Zhijian Ma", "affiliations": ["Alibaba Group"], "personId": "zhijian-ma" }, { "name": "Haibin Wang", "affiliations": ["Alibaba Group"], "personId": "haibin-wang" }, { "name": "Yaohua Wang", "affiliations": ["Alibaba Group"], "personId": "yaohua-wang" }, { "name": "Xiuyu Sun", "affiliations": ["Alibaba Group"], "personId": "xiuyu-sun" }, { "name": "Defu Lian", "affiliations": ["University of Science and Technology of China"], "personId": "defu-lian" }, { "name": "Bolin Ding", "affiliations": ["Alibaba Group"], "personId": "bolin-ding" }, { "name": "Jingren Zhou", "affiliations": ["Alibaba Group"], "personId": "jingren-zhou" } ], "affiliationSource": "https://arxiv.org/pdf/2405.06510v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-69a564882375", "catalogIds": ["ref-69a564882375"], "title": "LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation", "kind": "paper", "scope": "related", "date": "2024-10-28", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2410.21520v4", "metadataSource": "https://arxiv.org/abs/2410.21520", "checkedDate": "2026-10-25", "authors": [ { "name": "Xinrui He", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "xinrui-he" }, { "name": "Yikun Ban", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "yikun-ban" }, { "name": "Jiaru Zou", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "jiaru-zou" }, { "name": "Tianxin Wei", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "tianxin-wei" }, { "name": "Curtiss B. Cook", "affiliations": ["Mayo Clinic Arizona"], "personId": "curtiss-b-cook" }, { "name": "Jingrui He", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "jingrui-he" } ], "affiliationSource": "https://arxiv.org/pdf/2410.21520v4", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-951a1d42efbc", "catalogIds": ["ref-951a1d42efbc"], "title": "Large Language Models as Data Preprocessors", "kind": "paper", "scope": "related", "date": "2024", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://www.vldb.org/workshops/2024/proceedings/TaDA/TaDA.11.pdf", "metadataSource": "https://www.vldb.org/workshops/2024/proceedings/TaDA/TaDA.11.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "Haochen Zhang", "affiliations": ["Osaka University"], "personId": "haochen-zhang" }, { "name": "Yuyang Dong", "affiliations": ["NEC Corporation"], "personId": "yuyang-dong" }, { "name": "Chuan Xiao", "affiliations": ["Osaka University", "Nagoya University"], "personId": "chuan-xiao" }, { "name": "Masafumi Oyamada", "affiliations": ["NEC Corporation"], "personId": "masafumi-oyamada" } ], "affiliationSource": "https://www.vldb.org/workshops/2024/proceedings/TaDA/TaDA.11.pdf" }, { "id": "ref-27a51549dee0", "catalogIds": ["ref-27a51549dee0"], "title": "LLMs with User-defined Prompts as Generic Data Operators for Reliable Data Processing", "kind": "paper", "scope": "related", "date": "2023-12-26", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2312.16351v1", "metadataSource": "https://arxiv.org/abs/2312.16351", "checkedDate": "2026-10-25", "authors": [ { "name": "Luyi Ma", "affiliations": ["Walmart"], "personId": "luyi-ma" }, { "name": "Nikhil Thakurdesai", "affiliations": ["Walmart"], "personId": "nikhil-thakurdesai" }, { "name": "Jiao Chen", "affiliations": ["Walmart"], "personId": "jiao-chen" }, { "name": "Jianpeng Xu", "affiliations": ["Walmart"], "personId": "jianpeng-xu" }, { "name": "Evren Korpeoglu", "affiliations": ["Walmart"], "personId": "evren-korpeoglu" }, { "name": "Sushant Kumar", "affiliations": ["Walmart"], "personId": "sushant-kumar" }, { "name": "Kannan Achan", "affiliations": ["Walmart"], "personId": "kannan-achan" } ], "affiliationSource": "https://arxiv.org/html/2312.16351v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-612428ef67d8", "catalogIds": ["ref-612428ef67d8"], "title": "Relationalizing Tables with Large Language Models: The Promise and Challenges", "kind": "paper", "scope": "related", "date": "2024-05-13", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://api.crossref.org/works/10.1109%2FICDEW61823.2024.00045", "metadataSource": "https://api.crossref.org/works/10.1109%2FICDEW61823.2024.00045", "checkedDate": "2026-10-25", "authors": [ { "name": "Zezhou Huang", "affiliations": ["Columbia University,New York,United States"], "personId": "zezhou-huang" }, { "name": "Eugene Wu", "affiliations": ["DSI, Columbia University,New York,United States"], "personId": "eugene-wu" } ], "affiliationSource": "https://api.crossref.org/works/10.1109%2FICDEW61823.2024.00045" }, { "id": "ref-53b225c975c0", "catalogIds": ["ref-53b225c975c0"], "title": "Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks", "kind": "paper", "scope": "related", "date": "2024-06", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://www.microsoft.com/en-us/research/wp-content/uploads/2024/04/Table-GPT.pdf", "metadataSource": "https://www.microsoft.com/en-us/research/wp-content/uploads/2024/04/Table-GPT.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "Peng Li", "affiliations": ["Georgia Institute of Technology"], "personId": "peng-li" }, { "name": "Yeye He", "affiliations": ["Microsoft Research"], "personId": "yeye-he" }, { "name": "Dror Yashar", "affiliations": ["Microsoft"], "personId": "dror-yashar" }, { "name": "Weiwei Cui", "affiliations": ["Microsoft Research"], "personId": "weiwei-cui" }, { "name": "Song Ge", "affiliations": ["Microsoft Research"], "personId": "song-ge" }, { "name": "Haidong Zhang", "affiliations": ["Microsoft Research"], "personId": "haidong-zhang" }, { "name": "Danielle Rifinski Fainman", "affiliations": ["Microsoft"], "personId": "danielle-rifinski-fainman" }, { "name": "Dongmei Zhang", "affiliations": ["Microsoft Research"], "personId": "dongmei-zhang" }, { "name": "Surajit Chaudhuri", "affiliations": ["Microsoft Research"], "personId": "surajit-chaudhuri" } ], "affiliationSource": "https://www.microsoft.com/en-us/research/wp-content/uploads/2024/04/Table-GPT.pdf" }, { "id": "ref-c31673a03164", "catalogIds": ["ref-c31673a03164"], "title": "SANTOS: Relationship-based Semantic Table Union Search", "kind": "paper", "scope": "related", "date": "2022-09-27", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2209.13589v1", "metadataSource": "https://arxiv.org/abs/2209.13589", "checkedDate": "2026-10-25", "authors": [ { "name": "Aamod Khatiwada", "affiliations": ["Northeastern University"], "personId": "aamod-khatiwada" }, { "name": "Grace Fan", "affiliations": ["Northeastern University"], "personId": "grace-fan" }, { "name": "Roee Shraga", "affiliations": ["Northeastern University"], "personId": "roee-shraga" }, { "name": "Zixuan Chen", "affiliations": ["Northeastern University"], "personId": "zixuan-chen" }, { "name": "Wolfgang Gatterbauer", "affiliations": ["Northeastern University"], "personId": "wolfgang-gatterbauer" }, { "name": "Renée J. Miller", "affiliations": ["Northeastern University"], "personId": "renee-j-miller" }, { "name": "Mirek Riedewald", "affiliations": ["Northeastern University"], "personId": "mirek-riedewald" } ], "affiliationSource": "https://arxiv.org/html/2209.13589v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-7ef6e5010ea6", "catalogIds": ["ref-7ef6e5010ea6"], "title": "Towards Scalable Data Discovery", "kind": "paper", "scope": "related", "date": "2021", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://edbt2021proceedings.github.io/docs/p61.pdf", "metadataSource": "https://edbt2021proceedings.github.io/docs/p61.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "Javier Flores", "affiliations": ["Universitat Politècnica de Catalunya"], "personId": "javier-flores" }, { "name": "Sergi Nadal", "affiliations": ["Universitat Politècnica de Catalunya"], "personId": "sergi-nadal" }, { "name": "Oscar Romero", "affiliations": ["Universitat Politècnica de Catalunya"], "personId": "oscar-romero" } ], "affiliationSource": "https://edbt2021proceedings.github.io/docs/p61.pdf" }, { "id": "arxiv-2409-02038", "catalogIds": ["arxiv-2409-02038"], "title": "BEAVER: An Enterprise Benchmark for Text-to-SQL", "kind": "paper", "scope": "related", "date": "2024-09-03", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2409.02038v3", "metadataSource": "https://arxiv.org/abs/2409.02038", "checkedDate": "2026-10-25", "authors": [ { "name": "Peter Baile Chen", "affiliations": ["MIT"], "personId": "peter-baile-chen" }, { "name": "Devin Yang", "affiliations": ["MIT"], "personId": "devin-yang" }, { "name": "Weiyue Li", "affiliations": ["Harvard University"], "personId": "weiyue-li" }, { "name": "Fabian Wenz", "affiliations": ["Technical University of Munich", "MIT"], "personId": "fabian-wenz" }, { "name": "Yi Zhang", "affiliations": ["Greenshoe"], "personId": "yi-zhang" }, { "name": "Nesime Tatbul", "affiliations": ["Intel Labs", "MIT"], "personId": "nesime-tatbul" }, { "name": "Michael Cafarella", "affiliations": ["MIT"], "personId": "michael-cafarella" }, { "name": "Çağatay Demiralp", "affiliations": ["Amazon Web Services", "MIT"], "personId": "cagatay-demiralp" }, { "name": "Michael Stonebraker", "affiliations": ["MIT"], "personId": "michael-stonebraker" } ], "affiliationSource": "https://arxiv.org/html/2409.02038v3", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2504-04808", "catalogIds": ["arxiv-2504-04808"], "title": "ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines", "kind": "paper", "scope": "related", "date": "2025-04-07", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2504.04808v2", "metadataSource": "https://arxiv.org/abs/2504.04808", "checkedDate": "2026-10-25", "authors": [ { "name": "Tengjun Jin", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "tengjun-jin" }, { "name": "Yuxuan Zhu", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "yuxuan-zhu" }, { "name": "Daniel Kang", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "daniel-kang" } ], "affiliationSource": "https://arxiv.org/html/2504.04808v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "ref-6da435766c04", "catalogIds": ["ref-6da435766c04"], "title": "CAESURA: Language Models as Multi-Modal Query Planners", "kind": "paper", "scope": "related", "date": "2023-08-07", "topic": "LRO taxonomy, table-centric, and relational-data preparation sources", "url": "https://arxiv.org/abs/2308.03424v1", "metadataSource": "https://arxiv.org/abs/2308.03424v1", "checkedDate": "2026-10-25", "authors": [ { "name": "Matthias Urban", "affiliations": ["Technical University of Darmstadt"], "personId": "matthias-urban" }, { "name": "Carsten Binnig", "affiliations": ["Technical University of Darmstadt", "DFKI"], "personId": "carsten-binnig" } ], "affiliationSource": "https://vldb.org/cidrdb/papers/2024/p14-urban.pdf" }, { "id": "arxiv-2411-07763", "catalogIds": ["arxiv-2411-07763"], "title": "Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows", "kind": "paper", "scope": "related", "date": "2024-11-12", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2411.07763v2", "metadataSource": "https://arxiv.org/abs/2411.07763", "checkedDate": "2026-10-25", "authors": [ { "name": "Fangyu Lei", "affiliations": ["University of Hong Kong"], "personId": "fangyu-lei" }, { "name": "Jixuan Chen", "affiliations": ["University of Hong Kong"], "personId": "jixuan-chen" }, { "name": "Yuxiao Ye", "affiliations": ["University of Hong Kong"], "personId": "yuxiao-ye" }, { "name": "Ruisheng Cao", "affiliations": ["University of Hong Kong"], "personId": "ruisheng-cao" }, { "name": "Dongchan Shin", "affiliations": ["University of Hong Kong"], "personId": "dongchan-shin" }, { "name": "Hongjin Su", "affiliations": ["University of Hong Kong"], "personId": "hongjin-su" }, { "name": "Zhaoqing Suo", "affiliations": ["University of Hong Kong"], "personId": "zhaoqing-suo" }, { "name": "Hongcheng Gao", "affiliations": ["University of Hong Kong"], "personId": "hongcheng-gao" }, { "name": "Wenjing Hu", "affiliations": ["University of Hong Kong"], "personId": "wenjing-hu" }, { "name": "Pengcheng Yin", "affiliations": ["Google"], "personId": "pengcheng-yin" }, { "name": "Victor Zhong", "affiliations": ["University of Waterloo"], "personId": "victor-zhong" }, { "name": "Caiming Xiong", "affiliations": ["Salesforce Research"], "personId": "caiming-xiong" }, { "name": "Ruoxi Sun", "affiliations": ["Google"], "personId": "ruoxi-sun" }, { "name": "Qian Liu", "affiliations": ["Sea AI Lab"], "personId": "qian-liu" }, { "name": "Sida Wang", "affiliations": [], "personId": "sida-wang", "affiliationNote": "No affiliation marker for this author in the checked paper author block." }, { "name": "Tao Yu", "affiliations": ["University of Hong Kong"], "personId": "tao-yu" } ], "affiliationSource": "https://arxiv.org/pdf/2411.07763v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2305-03111", "catalogIds": ["arxiv-2305-03111"], "title": "Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs", "kind": "paper", "scope": "related", "date": "2023-05-04", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2305.03111v3", "metadataSource": "https://arxiv.org/abs/2305.03111", "checkedDate": "2026-10-25", "authors": [ { "name": "Jinyang Li", "affiliations": ["University of Hong Kong"], "personId": "jinyang-li" }, { "name": "Binyuan Hui", "affiliations": ["Alibaba Group"], "personId": "binyuan-hui" }, { "name": "Ge Qu", "affiliations": ["University of Hong Kong"], "personId": "ge-qu" }, { "name": "Jiaxi Yang", "affiliations": ["Alibaba Group"], "personId": "jiaxi-yang" }, { "name": "Binhua Li", "affiliations": ["Alibaba Group"], "personId": "binhua-li" }, { "name": "Bowen Li", "affiliations": ["The Chinese University of Hong Kong, Shenzhen"], "personId": "bowen-li" }, { "name": "Bailin Wang", "affiliations": ["MIT"], "personId": "bailin-wang" }, { "name": "Bowen Qin", "affiliations": ["Alibaba Group"], "personId": "bowen-qin" }, { "name": "Rongyu Cao", "affiliations": [], "personId": "rongyu-cao", "affiliationNote": "Listed in arXiv publication metadata, but absent from the checked PDF author block; affiliation unresolved." }, { "name": "Ruiying Geng", "affiliations": ["Alibaba Group"], "personId": "ruiying-geng" }, { "name": "Nan Huo", "affiliations": ["University of Hong Kong"], "personId": "nan-huo" }, { "name": "Xuanhe Zhou", "affiliations": ["Tsinghua University"], "personId": "xuanhe-zhou" }, { "name": "Chenhao Ma", "affiliations": ["The Chinese University of Hong Kong, Shenzhen"], "personId": "chenhao-ma" }, { "name": "Guoliang Li", "affiliations": ["Tsinghua University"], "personId": "guoliang-li" }, { "name": "Kevin C. C. Chang", "affiliations": ["University of Illinois Urbana-Champaign"], "personId": "kevin-c-c-chang" }, { "name": "Fei Huang", "affiliations": ["Alibaba Group"], "personId": "fei-huang" }, { "name": "Reynold Cheng", "affiliations": ["University of Hong Kong"], "personId": "reynold-cheng" }, { "name": "Yongbin Li", "affiliations": ["Alibaba Group"], "personId": "yongbin-li" } ], "affiliationSource": "https://arxiv.org/pdf/2305.03111v3", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2106-11455", "catalogIds": ["arxiv-2106-11455"], "title": "KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers", "kind": "paper", "scope": "related", "date": "2021-06-22", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2106.11455v1", "metadataSource": "https://arxiv.org/abs/2106.11455", "checkedDate": "2026-10-25", "authors": [ { "name": "Chia-Hsuan Lee", "affiliations": ["University of Washington"], "personId": "chia-hsuan-lee" }, { "name": "Oleksandr Polozov", "affiliations": ["Microsoft Research"], "personId": "oleksandr-polozov" }, { "name": "Matthew Richardson", "affiliations": ["Microsoft Research"], "personId": "matthew-richardson" } ], "affiliationSource": "https://arxiv.org/html/2106.11455v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2010-11246", "catalogIds": ["arxiv-2010-11246"], "title": "On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries", "kind": "paper", "scope": "related", "date": "2020-10-21", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2010.11246v1", "metadataSource": "https://arxiv.org/abs/2010.11246", "checkedDate": "2026-10-25", "authors": [ { "name": "Tianze Shi", "affiliations": ["Cornell University"], "personId": "tianze-shi" }, { "name": "Chen Zhao", "affiliations": ["University of Maryland"], "personId": "chen-zhao" }, { "name": "Jordan Boyd-Graber", "affiliations": ["University of Maryland"], "personId": "jordan-boyd-graber" }, { "name": "Hal Daumé III", "affiliations": ["Microsoft Research", "University of Maryland"], "personId": "hal-daume-iii" }, { "name": "Lillian Lee", "affiliations": ["Cornell University"], "personId": "lillian-lee" } ], "affiliationSource": "https://arxiv.org/html/2010.11246v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2509-24405", "catalogIds": ["arxiv-2509-24405"], "title": "Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language Agents", "kind": "paper", "scope": "related", "date": "2025-09-29", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2509.24405v1", "metadataSource": "https://arxiv.org/abs/2509.24405", "checkedDate": "2026-10-25", "authors": [ { "name": "Khanh Trinh Pham", "affiliations": ["Griffith University"], "personId": "khanh-trinh-pham" }, { "name": "Thu Huong Nguyen", "affiliations": ["Griffith University"], "personId": "thu-huong-nguyen" }, { "name": "Jun Jo", "affiliations": ["Griffith University"], "personId": "jun-jo" }, { "name": "Quoc Viet Hung Nguyen", "affiliations": ["Griffith University"], "personId": "quoc-viet-hung-nguyen" }, { "name": "Thanh Tam Nguyen", "affiliations": ["Griffith University"], "personId": "thanh-tam-nguyen" } ], "affiliationSource": "https://arxiv.org/html/2509.24405v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2510-07309", "catalogIds": ["arxiv-2510-07309"], "title": "Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain", "kind": "paper", "scope": "related", "date": "2025-10-08", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2510.07309v4", "metadataSource": "https://arxiv.org/abs/2510.07309", "checkedDate": "2026-10-25", "authors": [ { "name": "Yue Li", "affiliations": ["Cornell University"], "personId": "yue-li" }, { "name": "Ran Tao", "affiliations": ["Cornell University"], "personId": "ran-tao" }, { "name": "Derek Hommel", "affiliations": ["Gena AI"], "personId": "derek-hommel" }, { "name": "Yusuf Denizay Dönder", "affiliations": ["Gena AI"], "personId": "yusuf-denizay-donder" }, { "name": "Sungyong Chang", "affiliations": ["Cornell University"], "personId": "sungyong-chang" }, { "name": "David Mimno", "affiliations": ["Cornell University"], "personId": "david-mimno" }, { "name": "Unso Eun Seo Jo", "affiliations": ["Cornell University", "Gena AI"], "personId": "unso-eun-seo-jo" } ], "affiliationSource": "https://arxiv.org/html/2510.07309v4", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2511-17190", "catalogIds": ["arxiv-2511-17190"], "title": "AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale", "kind": "paper", "scope": "related", "date": "2025-11-21", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2511.17190v1", "metadataSource": "https://arxiv.org/abs/2511.17190", "checkedDate": "2026-10-25", "authors": [ { "name": "Ziyang Wang", "affiliations": ["Huazhong University of Science and Technology"], "personId": "ziyang-wang" }, { "name": "Yuanlei Zheng", "affiliations": ["Huazhong University of Science and Technology"], "personId": "yuanlei-zheng" }, { "name": "Zhenbiao Cao", "affiliations": ["Huazhong University of Science and Technology"], "personId": "zhenbiao-cao" }, { "name": "Xiaojin Zhang", "affiliations": ["Huazhong University of Science and Technology"], "personId": "xiaojin-zhang" }, { "name": "Zhongyu Wei", "affiliations": ["Fudan University"], "personId": "zhongyu-wei" }, { "name": "Pei Fu", "affiliations": ["Xiaomi"], "personId": "pei-fu" }, { "name": "Zhenbo Luo", "affiliations": ["Xiaomi"], "personId": "zhenbo-luo" }, { "name": "Wei Chen", "affiliations": ["Huazhong University of Science and Technology"], "personId": "wei-chen" }, { "name": "Xiang Bai", "affiliations": ["Huazhong University of Science and Technology"], "personId": "xiang-bai" } ], "affiliationSource": "https://arxiv.org/pdf/2511.17190v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2502-00675", "catalogIds": ["arxiv-2502-00675"], "title": "ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration", "kind": "paper", "scope": "related", "date": "2025-02-02", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2502.00675v5", "metadataSource": "https://arxiv.org/abs/2502.00675", "checkedDate": "2026-10-25", "authors": [ { "name": "Minghang Deng", "affiliations": ["UC San Diego"], "personId": "minghang-deng" }, { "name": "Ashwin Ramachandran", "affiliations": ["UC San Diego"], "personId": "ashwin-ramachandran" }, { "name": "Canwen Xu", "affiliations": ["Snowflake"], "personId": "canwen-xu" }, { "name": "Lanxiang Hu", "affiliations": ["UC San Diego", "Snowflake"], "personId": "lanxiang-hu" }, { "name": "Zhewei Yao", "affiliations": ["Snowflake"], "personId": "zhewei-yao" }, { "name": "Anupam Datta", "affiliations": ["Snowflake"], "personId": "anupam-datta" }, { "name": "Hao Zhang", "affiliations": ["UC San Diego", "Snowflake"], "personId": "hao-zhang-ucsd" } ], "affiliationSource": "https://arxiv.org/pdf/2502.00675v5", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2511-21402", "catalogIds": ["arxiv-2511-21402"], "title": "Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation", "kind": "paper", "scope": "related", "date": "2025-11-26", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2511.21402v1", "metadataSource": "https://arxiv.org/abs/2511.21402", "checkedDate": "2026-10-25", "authors": [ { "name": "Zhifeng Hao", "affiliations": ["Guangdong University of Technology", "Shantou University"], "personId": "zhifeng-hao" }, { "name": "Qibin Song", "affiliations": ["Guangdong University of Technology"], "personId": "qibin-song" }, { "name": "Ruichu Cai", "affiliations": ["Guangdong University of Technology", "Peng Cheng Laboratory"], "personId": "ruichu-cai" }, { "name": "Boyan Xu", "affiliations": ["Guangdong University of Technology"], "personId": "boyan-xu" } ], "affiliationSource": "https://arxiv.org/html/2511.21402v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2602-16720", "catalogIds": ["arxiv-2602-16720"], "title": "APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL", "kind": "paper", "scope": "related", "date": "2026-02-11", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2602.16720v2", "metadataSource": "https://arxiv.org/abs/2602.16720", "checkedDate": "2026-10-25", "authors": [ { "name": "Bowen Cao", "affiliations": ["The Chinese University of Hong Kong"], "personId": "bowen-cao" }, { "name": "Weibin Liao", "affiliations": ["Peking University"], "personId": "weibin-liao" }, { "name": "Yushi Sun", "affiliations": ["Tencent LIGHTSPEED"], "personId": "yushi-sun" }, { "name": "Dong Fang", "affiliations": ["Tencent LIGHTSPEED"], "personId": "dong-fang" }, { "name": "Haitao Li", "affiliations": ["Tencent LIGHTSPEED"], "personId": "haitao-li" }, { "name": "Wai Lam", "affiliations": ["The Chinese University of Hong Kong"], "personId": "wai-lam" } ], "affiliationSource": "https://arxiv.org/html/2602.16720v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2408-04667", "catalogIds": ["arxiv-2408-04667"], "title": "Non-Determinism of \"Deterministic\" LLM Settings", "kind": "paper", "scope": "related", "date": "2024-08-06", "topic": "AI-native SQL generation and text-to-SQL benchmark sources", "url": "https://arxiv.org/abs/2408.04667v5", "metadataSource": "https://arxiv.org/abs/2408.04667", "checkedDate": "2026-10-25", "authors": [ { "name": "Berk Atil", "affiliations": ["Pennsylvania State University"], "personId": "berk-atil" }, { "name": "Sarp Aykent", "affiliations": ["Comcast"], "personId": "sarp-aykent" }, { "name": "Alexa Chittams", "affiliations": ["Comcast"], "personId": "alexa-chittams" }, { "name": "Lisheng Fu", "affiliations": ["Comcast"], "personId": "lisheng-fu" }, { "name": "Rebecca J. Passonneau", "affiliations": ["Pennsylvania State University"], "personId": "rebecca-j-passonneau" }, { "name": "Evan Radcliffe", "affiliations": ["Comcast"], "personId": "evan-radcliffe" }, { "name": "Guru Rajan Rajagopal", "affiliations": ["Comcast"], "personId": "guru-rajan-rajagopal" }, { "name": "Adam Sloan", "affiliations": ["Comcast"], "personId": "adam-sloan" }, { "name": "Tomasz Tudrej", "affiliations": ["Comcast"], "personId": "tomasz-tudrej" }, { "name": "Ferhan Ture", "affiliations": ["Comcast"], "personId": "ferhan-ture" }, { "name": "Zhe Wu", "affiliations": ["Comcast"], "personId": "zhe-wu" }, { "name": "Lixinyu Xu", "affiliations": ["Comcast"], "personId": "lixinyu-xu" }, { "name": "Breck Baldwin", "affiliations": ["Comcast"], "personId": "breck-baldwin" } ], "affiliationSource": "https://arxiv.org/html/2408.04667v5", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2210-02875", "catalogIds": ["arxiv-2210-02875"], "title": "Binding Language Models in Symbolic Languages", "kind": "paper", "scope": "related", "date": "2022-10-06", "topic": "Hybrid query and neural-symbolic systems", "url": "https://arxiv.org/abs/2210.02875v2", "metadataSource": "https://arxiv.org/abs/2210.02875", "checkedDate": "2026-10-25", "authors": [ { "name": "Zhoujun Cheng", "affiliations": ["University of Hong Kong", "Shanghai Jiao Tong University"], "personId": "zhoujun-cheng" }, { "name": "Tianbao Xie", "affiliations": ["University of Hong Kong"], "personId": "tianbao-xie" }, { "name": "Peng Shi", "affiliations": ["University of Waterloo"], "personId": "peng-shi" }, { "name": "Chengzu Li", "affiliations": ["University of Hong Kong"], "personId": "chengzu-li" }, { "name": "Rahul Nadkarni", "affiliations": ["University of Washington"], "personId": "rahul-nadkarni" }, { "name": "Yushi Hu", "affiliations": ["University of Washington"], "personId": "yushi-hu" }, { "name": "Caiming Xiong", "affiliations": ["Salesforce Research"], "personId": "caiming-xiong" }, { "name": "Dragomir Radev", "affiliations": ["Yale University"], "personId": "dragomir-radev" }, { "name": "Mari Ostendorf", "affiliations": ["University of Washington"], "personId": "mari-ostendorf" }, { "name": "Luke Zettlemoyer", "affiliations": ["University of Washington", "Meta"], "personId": "luke-zettlemoyer" }, { "name": "Noah A. Smith", "affiliations": ["University of Washington", "Allen Institute for AI"], "personId": "noah-a-smith" }, { "name": "Tao Yu", "affiliations": ["University of Hong Kong", "University of Washington"], "personId": "tao-yu" } ], "affiliationSource": "https://arxiv.org/pdf/2210.02875v2", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2312-13264", "catalogIds": ["arxiv-2312-13264"], "title": "dIR -- Discrete Information Retrieval: Conversational Search over Unstructured (and Structured) Data with Large Language Models", "kind": "paper", "scope": "related", "date": "2023-12-20", "topic": "Hybrid query and neural-symbolic systems", "url": "https://arxiv.org/abs/2312.13264v1", "metadataSource": "https://arxiv.org/abs/2312.13264", "checkedDate": "2026-10-25", "authors": [ { "name": "Pablo M. Rodriguez Bertorello", "affiliations": ["Stanford University"], "personId": "pablo-m-rodriguez-bertorello" }, { "name": "Jean Rodmond Junior Laguerre", "affiliations": ["Stanford University"], "personId": "jean-rodmond-junior-laguerre" } ], "affiliationSource": "https://arxiv.org/pdf/2312.13264v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2304-09433", "catalogIds": ["arxiv-2304-09433"], "title": "Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes", "kind": "paper", "scope": "related", "date": "2023-04-19", "topic": "Adjacent data management and extraction systems", "url": "https://arxiv.org/abs/2304.09433v3", "metadataSource": "https://arxiv.org/abs/2304.09433", "checkedDate": "2026-10-25", "authors": [ { "name": "Simran Arora", "affiliations": ["Stanford University"], "personId": "simran-arora" }, { "name": "Brandon Yang", "affiliations": ["Stanford University"], "personId": "brandon-yang" }, { "name": "Sabri Eyuboglu", "affiliations": ["Stanford University"], "personId": "sabri-eyuboglu" }, { "name": "Avanika Narayan", "affiliations": ["Stanford University"], "personId": "avanika-narayan" }, { "name": "Andrew Hojel", "affiliations": ["Stanford University"], "personId": "andrew-hojel" }, { "name": "Immanuel Trummer", "affiliations": ["Cornell University"], "personId": "immanuel-trummer" }, { "name": "Christopher Ré", "affiliations": ["Stanford University"], "personId": "christopher-re" } ], "affiliationSource": "https://arxiv.org/html/2304.09433v3", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "arxiv-2406-15652", "catalogIds": ["arxiv-2406-15652"], "title": "GenSQL: A Probabilistic Programming System for Querying Generative Models of Database Tables", "kind": "paper", "scope": "related", "date": "2024-06-21", "topic": "Adjacent data management and extraction systems", "url": "https://arxiv.org/abs/2406.15652v1", "metadataSource": "https://arxiv.org/abs/2406.15652", "checkedDate": "2026-10-25", "authors": [ { "name": "Mathieu Huot", "affiliations": ["MIT"], "personId": "mathieu-huot" }, { "name": "Matin Ghavami", "affiliations": ["MIT"], "personId": "matin-ghavami" }, { "name": "Alexander K. Lew", "affiliations": ["MIT"], "personId": "alexander-k-lew" }, { "name": "Ulrich Schaechtle", "affiliations": ["Digital Garage"], "personId": "ulrich-schaechtle" }, { "name": "Cameron E. Freer", "affiliations": ["MIT"], "personId": "cameron-e-freer" }, { "name": "Zane Shelby", "affiliations": ["Digital Garage"], "personId": "zane-shelby" }, { "name": "Martin C. Rinard", "affiliations": ["MIT"], "personId": "martin-c-rinard" }, { "name": "Feras A. Saad", "affiliations": ["Carnegie Mellon University"], "personId": "feras-a-saad" }, { "name": "Vikash K. Mansinghka", "affiliations": ["MIT"], "personId": "vikash-k-mansinghka" } ], "affiliationSource": "https://arxiv.org/html/2406.15652v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "semreuse", "catalogIds": ["semreuse"], "title": "SemReuse: Certified Reuse of Cached Natural-Language Views for Semantic Operators", "kind": "paper", "scope": "core", "date": "2026-10-12", "topic": "Optimization", "url": "https://arxiv.org/abs/2610.16035v1", "metadataSource": "https://arxiv.org/abs/2610.16035", "checkedDate": "2026-10-25", "authors": [ { "name": "Phat T. Tran-Truong", "affiliations": ["Vietnam National University"], "personId": "phat-t-tran-truong" }, { "name": "Tung Kieu", "affiliations": ["Aalborg University"], "personId": "tung-kieu" }, { "name": "Xuan-Bach Le", "affiliations": ["Vietnam National University"], "personId": "xuan-bach-le" }, { "name": "Son X. Ha", "affiliations": ["RMIT University"], "personId": "son-x-ha" }, { "name": "Duc Kieu", "affiliations": ["Deakin University"], "personId": "duc-kieu" }, { "name": "Bin Yang", "affiliations": ["East China Normal University"], "personId": "bin-yang" }, { "name": "Christian S. Jensen", "affiliations": ["Aalborg University"], "personId": "christian-s-jensen" } ], "affiliationSource": "https://arxiv.org/html/2610.16035v1", "affiliationReview": { "method": "paper-author-block", "checkedDate": "2026-10-25" } }, { "id": "imlane", "catalogIds": ["imlane"], "title": "IMLane: Composable Framework for Efficient AI Function Execution in Database Engine", "kind": "paper", "scope": "related", "date": "2026", "topic": "Optimization", "url": "https://www.vldb.org/pvldb/vol19/p4223-xu.pdf", "metadataSource": "https://www.vldb.org/pvldb/vol19/p4223-xu.pdf", "checkedDate": "2026-10-25", "authors": [ { "name": "Chenyang Zhang", "affiliations": ["East China Normal University"], "personId": "chenyang-zhang" }, { "name": "Linjun Lu", "affiliations": ["East China Normal University"], "personId": "linjun-lu" }, { "name": "Qingfeng Pan", "affiliations": ["East China Normal University"], "personId": "qingfeng-pan" }, { "name": "Chen Xu", "affiliations": ["East China Normal University"], "personId": "chen-xu" }, { "name": "Xianzhong Cao", "affiliations": ["East China Normal University"], "personId": "xianzhong-cao" }, { "name": "Quanqing Xu", "affiliations": ["OceanBase, AntGroup"], "personId": "quanqing-xu" }, { "name": "Chuanhui Yang", "affiliations": ["OceanBase, AntGroup"], "personId": "chuanhui-yang" } ], "affiliationSource": "https://www.vldb.org/pvldb/vol19/p4223-xu.pdf" }, { "id": "moar", "title": "Multi-Objective Agentic Rewrites for Unstructured Data Processing", "kind": "paper", "date": "2025-12-02", "topic": "Query optimization", "url": "https://arxiv.org/abs/2512.02289v4", "affiliationSource": "https://arxiv.org/html/2512.02289v4", "authors": [ { "name": "Lindsey Linxi Wei", "affiliations": ["University of Washington"], "personId": "lindsey-linxi-wei" }, { "name": "Shreya Shankar", "affiliations": ["UC Berkeley"], "personId": "shreya-shankar" }, { "name": "Sepanta Zeighami", "affiliations": ["UC Berkeley"], "personId": "sepanta-zeighami" }, { "name": "Yeounoh Chung", "affiliations": ["Google"], "personId": "yeounoh-chung" }, { "name": "Fatma Ozcan", "affiliations": ["Google"], "personId": "fatma-ozcan" }, { "name": "Aditya G. Parameswaran", "affiliations": ["UC Berkeley"], "personId": "aditya-g-parameswaran" } ], "scope": "core", "catalogIds": [], "checkedDate": "2026-10-24" }, { "id": "quail-blog", "title": "Building an Ultra-High Throughput AI-SQL Engine", "kind": "blog", "date": "2026-09-24", "topic": "Inference optimization", "url": "https://fsdatalab.github.io/blog/introducing-quail/", "authors": [ { "name": "Shreya Shankar", "affiliations": [], "personId": "shreya-shankar", "affiliationNote": "The article byline does not specify author affiliations." }, { "name": "Charles Frye", "affiliations": [], "personId": "charles-frye", "affiliationNote": "The article byline does not specify author affiliations." }, { "name": "Fergus Finn", "affiliations": [], "personId": "fergus-finn", "affiliationNote": "The article byline does not specify author affiliations." }, { "name": "Arnav Dhariya", "affiliations": [], "personId": "arnav-dhariya", "affiliationNote": "The article byline does not specify author affiliations." }, { "name": "Joseph Barrow", "affiliations": [], "personId": "joseph-barrow", "affiliationNote": "The article byline does not specify author affiliations." }, { "name": "Meryem Arik", "affiliations": [], "personId": "meryem-arik", "affiliationNote": "The article byline does not specify author affiliations." } ], "scope": "core", "catalogIds": [], "checkedDate": "2026-10-24" } ] }