People of SQPE

• PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query PlansCore SQPE paper · 2026-04-10Affiliation source: UC Berkeley
• Task Cascades for Efficient Unstructured Data ProcessingRelated / background paper · 2026-01-09Affiliation source: UC Berkeley
• Featurized-Decomposition Join: Low-Cost Semantic Joins with GuaranteesCore SQPE paper · 2025-12-05Affiliation source: UC Berkeley
• Multi-Objective Agentic Rewrites for Unstructured Data ProcessingCore SQPE paper · 2025-12-02Affiliation source: UC Berkeley
• Cut Costs, Not Accuracy: LLM-Powered Data Processing with GuaranteesRelated / background paper · 2025-09-02Affiliation source: UC Berkeley
• DocETL: Agentic Query Rewriting and Evaluation for Complex Document ProcessingCore SQPE paper · 2024-10-16Affiliation source: UC Berkeley

Coauthors in this collection: Shreya Shankar, Tristan Chambers, Tarak Shah, Eugene Wu, Qiuyang Mang, Yufan Xiang, Hangrui Zhou, Runyuan He, Jiaxiang Yu, Hanchen Li, Alvin Cheung, Sepanta Zeighami, Lindsey Linxi Wei, Yeounoh Chung, Fatma Özcan.

• Prune First, Decide Fast: Scalable Semantic Query Processing with JEVDBCore SQPE paper · 2026-10-01Affiliation source: Purdue University
• SemJoin: Semantic Join OptimizationCore SQPE paper · 2026-06-28Affiliation source: Purdue University
• iPDB -- Optimizing Semantic SQL QueriesCore SQPE paper · 2026-01-23Affiliation source: Purdue University
• Abacus: A Cost-Based Optimizer for Semantic Operator SystemsRelated / background paper · 2025-05-20Affiliation source: MIT
• A Declarative System for Optimizing AI WorkloadsCore SQPE paper · 2024-05-23Affiliation source: MIT

Coauthors in this collection: Matthew Russo, Michael Cafarella, Lei Cao, Peter Baille Chen, Zui Chen, Michael Franklin, Tim Kraska, Samuel Madden, Gerardo Vitagliano, Zhengle Wang, Hanxu Yan, Fuheng Zhao, Udesh Kumarasinghe, Tyler Liu, Ahmed R. Mahmood, Walid G. Aref, Christopher Gou, Aditya Banerjee, Jiaxuan Wang, Sivaprasad Sudhir.

• The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI OperatorsCore SQPE paper · 2026-09-17Affiliation source: Google
• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]Core SQPE paper · 2026-05-18Affiliation source: Google
• Multi-Objective Agentic Rewrites for Unstructured Data ProcessingCore SQPE paper · 2025-12-02Affiliation source: Google
• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: Google

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer, Tarfah Alrashed, Per Jacobsson, Tal Neiman, Xianshun Chen, Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Yves-Laurent Kom Samo, Pushkar Khadilkar, Sam Idicula, Alon Halevy, Yannis Papakonstantinou, Lindsey Linxi Wei, Shreya Shankar, Sepanta Zeighami, Aditya G. Parameswaran.

• Larch: Learned Query Optimization for Semantic PredicatesCore SQPE paper · 2026-06-06Affiliation source: Snowflake
• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake
• Access Paths for Efficient Ordering with Large Language ModelsCore SQPE paper · 2025-08-30Affiliation source: Snowflake
• ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column ExplorationRelated / background paper · 2025-02-02Affiliation source: Snowflake

Coauthors in this collection: Fuheng Zhao, Jiayue Chen, Yiming Pan, Tahseen Rabbani, Sohaib, Divyakant Agrawal, Amr El Abbadi, Paritosh Aggarwal, Dimitris Tsirogiannis, Paweł Liskowski, Zihan Li, Benjamin Han, Puxuan Yu, Varich Boonsanong, Bowei Chen, Boxin Jiang, Nitish Jindal, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Nathan Wiegand, Minghang Deng, Ashwin Ramachandran, Canwen Xu, Lanxiang Hu, Zhewei Yao, Hao Zhang.

• Larch: Learned Query Optimization for Semantic PredicatesCore SQPE paper · 2026-06-06Affiliation source: Snowflake
• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake
• Access Paths for Efficient Ordering with Large Language ModelsCore SQPE paper · 2025-08-30Affiliation source: Snowflake

Coauthors in this collection: Fuheng Zhao, Jiayue Chen, Yiming Pan, Tahseen Rabbani, Sohaib, Divyakant Agrawal, Amr El Abbadi, Paritosh Aggarwal, Anupam Datta, Paweł Liskowski, Zihan Li, Benjamin Han, Puxuan Yu, Varich Boonsanong, Bowei Chen, Boxin Jiang, Nitish Jindal, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Nathan Wiegand.

• Prune First, Decide Fast: Scalable Semantic Query Processing with JEVDBCore SQPE paper · 2026-10-01Affiliation source: University of Utah
• Larch: Learned Query Optimization for Semantic PredicatesCore SQPE paper · 2026-06-06Affiliation source: Snowflake
• Access Paths for Efficient Ordering with Large Language ModelsCore SQPE paper · 2025-08-30Affiliation source: University of Utah
• Hybrid Querying Over Relational Databases and Large Language ModelsRelated / background paper · 2024-08-01Affiliation source: UC Santa Barbara

Coauthors in this collection: Zhengle Wang, Hanxu Yan, Chunwei Liu, Jiayue Chen, Yiming Pan, Tahseen Rabbani, Sohaib, Divyakant Agrawal, Amr El Abbadi, Paritosh Aggarwal, Anupam Datta, Dimitris Tsirogiannis, Paweł Liskowski, Zihan Li, Benjamin Han, Puxuan Yu, Varich Boonsanong.

• Building an Ultra-High Throughput AI-SQL EngineTechnical article · 2026-09-24The article byline does not specify author affiliations.
• Task Cascades for Efficient Unstructured Data ProcessingRelated / background paper · 2026-01-09Affiliation source: UC Berkeley
• Featurized-Decomposition Join: Low-Cost Semantic Joins with GuaranteesCore SQPE paper · 2025-12-05Affiliation source: UC Berkeley
• Multi-Objective Agentic Rewrites for Unstructured Data ProcessingCore SQPE paper · 2025-12-02Affiliation source: UC Berkeley
• Cut Costs, Not Accuracy: LLM-Powered Data Processing with GuaranteesRelated / background paper · 2025-09-02Affiliation source: UC Berkeley
• DocETL: Agentic Query Rewriting and Evaluation for Complex Document ProcessingCore SQPE paper · 2024-10-16Affiliation source: UC Berkeley

Coauthors in this collection: Tristan Chambers, Tarak Shah, Aditya G. Parameswaran, Eugene Wu, Sepanta Zeighami, Lindsey Linxi Wei, Yeounoh Chung, Fatma Özcan, Charles Frye, Fergus Finn, Arnav Dhariya, Joseph Barrow, Meryem Arik.

• Larch: Learned Query Optimization for Semantic PredicatesCore SQPE paper · 2026-06-06Affiliation source: Snowflake
• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Fuheng Zhao, Paweł Liskowski, Zihan Li, Puxuan Yu, Varich Boonsanong, Dimitris Tsirogiannis, Anupam Datta, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Nitish Jindal, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Nathan Wiegand.

• Same Query, Different Answer: Run-to-Run Variance in Semantic Query ProcessingCore SQPE paper · 2026-10-09Affiliation source: IBM
• Semantic Views: Certified Reuse of LLM Labels Across Semantic QueriesCore SQPE paper · 2026-10-08Affiliation source: IBM

Coauthors in this collection: Oktie Hassanzadeh.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: MIT
• Abacus: A Cost-Based Optimizer for Semantic Operator SystemsRelated / background paper · 2025-05-20Affiliation source: MIT
• A Declarative System for Optimizing AI WorkloadsCore SQPE paper · 2024-05-23Affiliation source: MIT

Coauthors in this collection: Chunwei Liu, Matthew Russo, Michael Cafarella, Lei Cao, Peter Baille Chen, Zui Chen, Michael Franklin, Tim Kraska, Samuel Madden, Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer, Sivaprasad Sudhir.

• KEN: An Execution Engine for Unstructured Database SystemsRelated / background paper · 2026Affiliation source: University of Arizona
• Unstructured Data Analysis using LLMs: A Comprehensive BenchmarkCore SQPE paper · 2025-10-31Affiliation source: University of Arizona · MIT
• QUEST: Query Optimization in Unstructured Document AnalysisRelated / background paper · 2025-07-09Affiliation source: MIT · University of Arizona
• A Declarative System for Optimizing AI WorkloadsCore SQPE paper · 2024-05-23Affiliation source: University of Arizona

Coauthors in this collection: Chunwei Liu, Matthew Russo, Michael Cafarella, Peter Baille Chen, Zui Chen, Michael Franklin, Tim Kraska, Samuel Madden, Gerardo Vitagliano, Qiyan Deng, Jianhui Li, Chengliang Chai, Jinqi Liu, Junzhi She, Kaisen Jin, Zhaoze Sun, Yuhao Deng, Jia Yuan, Ye Yuan, Guoren Wang, Xinyu Guo, Han Han, Ferdi Kossmann, Ziniu Wu, Alex Turk, Nesime Tatbul.

• Text2SQL is Not Enough: Unifying AI and Databases with TAGRelated / background paper · 2024-08-27Affiliation source: Stanford University
• Semantic Operators: A Declarative Model for Rich, AI-based Data ProcessingCore SQPE paper · 2024-07-16Affiliation source: Stanford University
• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: Stanford University

Coauthors in this collection: Siddharth Jha, Melissa Pan, Harshit Gupta, Parth Asawa, Carlos Guestrin, Matei Zaharia, Shu Liu, Asim Biswal, Amog Kamsetty, Audrey Cheng, Luis Gaspar Schroeder, Shiyi Cao, Xiangxi Mo, Ion Stoica, Joseph E. Gonzalez, Siddarth Jha.

• Text2SQL is Not Enough: Unifying AI and Databases with TAGRelated / background paper · 2024-08-27Affiliation source: UC Berkeley
• Semantic Operators: A Declarative Model for Rich, AI-based Data ProcessingCore SQPE paper · 2024-07-16Affiliation source: UC Berkeley
• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: UC Berkeley
• Accelerating Approximate Aggregation Queries with Expensive PredicatesRelated / background paper · 2021Affiliation source: Stanford University
• Approximate Selection with Guarantees using ProxiesRelated / background paper · 2020Affiliation source: Stanford University
• BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video AnalyticsRelated / background paper · 2018-05-02Affiliation source: Stanford University
• NoScope: Optimizing Neural Network Queries over Video at ScaleRelated / background paper · 2017Affiliation source: Stanford University

Coauthors in this collection: Liana Patel, Siddharth Jha, Melissa Pan, Harshit Gupta, Parth Asawa, Carlos Guestrin, Shu Liu, Asim Biswal, Amog Kamsetty, Audrey Cheng, Luis Gaspar Schroeder, Shiyi Cao, Xiangxi Mo, Ion Stoica, Joseph E. Gonzalez, Daniel Kang, Edward Gan, Peter Bailis, Tatsunori Hashimoto, John Guibas, Yi Sun, John Emmons, Firas Abuzaid, Siddarth Jha.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: MIT
• Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven AnalyticsRelated / background paper · 2025-09-02Affiliation source: MIT
• Abacus: A Cost-Based Optimizer for Semantic Operator SystemsRelated / background paper · 2025-05-20Affiliation source: MIT
• A Declarative System for Optimizing AI WorkloadsCore SQPE paper · 2024-05-23Affiliation source: MIT

Coauthors in this collection: Chunwei Liu, Michael Cafarella, Lei Cao, Peter Baille Chen, Zui Chen, Michael Franklin, Tim Kraska, Samuel Madden, Gerardo Vitagliano, Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer, Sivaprasad Sudhir.

• Same Query, Different Answer: Run-to-Run Variance in Semantic Query ProcessingCore SQPE paper · 2026-10-09Affiliation source: IBM
• Semantic Views: Certified Reuse of LLM Labels Across Semantic QueriesCore SQPE paper · 2026-10-08Affiliation source: IBM

Coauthors in this collection: Dharmashankar Subramanian.

• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake
• Access Paths for Efficient Ordering with Large Language ModelsCore SQPE paper · 2025-08-30Affiliation source: Snowflake

Coauthors in this collection: Fuheng Zhao, Jiayue Chen, Yiming Pan, Tahseen Rabbani, Sohaib, Divyakant Agrawal, Amr El Abbadi, Anupam Datta, Dimitris Tsirogiannis, Paweł Liskowski, Benjamin Han, Bowei Chen, Boxin Jiang, Nitish Jindal, Zihan Li, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Nathan Wiegand.

• Larch: Learned Query Optimization for Semantic PredicatesCore SQPE paper · 2026-06-06Affiliation source: Snowflake
• Streaming Model Cascades for Semantic SQLRelated / background paper · 2026-04-01Affiliation source: Snowflake
• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Fuheng Zhao, Zihan Li, Benjamin Han, Puxuan Yu, Varich Boonsanong, Dimitris Tsirogiannis, Anupam Datta, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Nitish Jindal, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Nathan Wiegand.

• Task Cascades for Efficient Unstructured Data ProcessingRelated / background paper · 2026-01-09Affiliation source: UC Berkeley
• Featurized-Decomposition Join: Low-Cost Semantic Joins with GuaranteesCore SQPE paper · 2025-12-05Affiliation source: UC Berkeley
• Multi-Objective Agentic Rewrites for Unstructured Data ProcessingCore SQPE paper · 2025-12-02Affiliation source: UC Berkeley
• Cut Costs, Not Accuracy: LLM-Powered Data Processing with GuaranteesRelated / background paper · 2025-09-02Affiliation source: UC Berkeley

Coauthors in this collection: Shreya Shankar, Aditya G. Parameswaran, Lindsey Linxi Wei, Yeounoh Chung, Fatma Özcan.

• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]Core SQPE paper · 2026-05-18Affiliation source: Google
• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: Google

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer, Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Yves-Laurent Kom Samo, Pushkar Khadilkar, Xianshun Chen, Sam Idicula, Alon Halevy, Yannis Papakonstantinou.

• The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI OperatorsCore SQPE paper · 2026-09-17Affiliation source: Google
• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]Core SQPE paper · 2026-05-18Affiliation source: Google

Coauthors in this collection: Tarfah Alrashed, Fatma Özcan, Per Jacobsson, Tal Neiman, Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Khadilkar, Sam Idicula, Alon Halevy, Yannis Papakonstantinou.

• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]Core SQPE paper · 2026-05-18Affiliation source: Google
• Multi-Objective Agentic Rewrites for Unstructured Data ProcessingCore SQPE paper · 2025-12-02Affiliation source: Google

Coauthors in this collection: Rushabh Desai, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Khadilkar, Xianshun Chen, Sam Idicula, Fatma Özcan, Alon Halevy, Yannis Papakonstantinou, Lindsey Linxi Wei, Shreya Shankar, Sepanta Zeighami, Aditya G. Parameswaran.

• From Interpretation to Compilation: A Compilation-Based Execution Engine for Semantic Operator SystemsCore SQPE paper · 2026-08-07Affiliation source: University of Hawaii at Manoa
• Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal DataCore SQPE paper · 2026-02-02Affiliation source: University of Hawaii at Manoa

Coauthors in this collection: Wenkai Dong, Ruyu Li, Tinghui Zhang, Haodi Ma, Daisy Zhe Wang.

• Benchmarking Hybrid Deep Research Across Database Querying and Web SearchCore SQPE paper · 2026-09-08Affiliation source: Snowflake
• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsCore SQPE paper · 2026-07-07Affiliation source: Snowflake

Coauthors in this collection: Tianyang Liu, Canwen Xu, Fangyu Lei, Nikki Lijing Kuang, Jixuan Chen, Tao Yu, Julian McAuley, Zhewei Yao, Ruofan Wu, Peiran Xu, Xiaolong Li, Fan Shu, Soyoung Yoon, Yite Wang, Xiaodong Yu, Boyi Liu, Feng Yan, Debiao Li.

• Benchmarking Hybrid Deep Research Across Database Querying and Web SearchCore SQPE paper · 2026-09-08Affiliation source: Snowflake
• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsCore SQPE paper · 2026-07-07Affiliation source: Snowflake
• ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column ExplorationRelated / background paper · 2025-02-02Affiliation source: Snowflake

Coauthors in this collection: Tianyang Liu, Canwen Xu, Fangyu Lei, Nikki Lijing Kuang, Jixuan Chen, Tao Yu, Julian McAuley, Yuxiong He, Ruofan Wu, Peiran Xu, Xiaolong Li, Fan Shu, Soyoung Yoon, Yite Wang, Xiaodong Yu, Boyi Liu, Feng Yan, Debiao Li, Minghang Deng, Ashwin Ramachandran, Lanxiang Hu, Anupam Datta, Hao Zhang.

• Larch: Learned Query Optimization for Semantic PredicatesCore SQPE paper · 2026-06-06Affiliation source: Snowflake
• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Fuheng Zhao, Paweł Liskowski, Benjamin Han, Puxuan Yu, Varich Boonsanong, Dimitris Tsirogiannis, Anupam Datta, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Nitish Jindal, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Nathan Wiegand.

• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Paweł Liskowski, Benjamin Han, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Nitish Jindal, Zihan Li, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Anupam Datta, Nathan Wiegand, Dimitris Tsirogiannis.

• SemJoin: Semantic Join OptimizationCore SQPE paper · 2026-06-28Affiliation source: Purdue University

Coauthors in this collection: Christopher Gou, Jiaxuan Wang, Chunwei Liu.

• iPDB -- Optimizing Semantic SQL QueriesCore SQPE paper · 2026-01-23Affiliation source: Google

Coauthors in this collection: Udesh Kumarasinghe, Tyler Liu, Chunwei Liu, Walid G. Aref.

• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]Core SQPE paper · 2026-05-18Affiliation source: Google

Coauthors in this collection: Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Khadilkar, Xianshun Chen, Sam Idicula, Fatma Özcan, Yannis Papakonstantinou.

• PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query PlansCore SQPE paper · 2026-04-10Affiliation source: UC Berkeley

Coauthors in this collection: Qiuyang Mang, Yufan Xiang, Hangrui Zhou, Runyuan He, Jiaxiang Yu, Hanchen Li, Aditya G. Parameswaran.

• Factorized and Vectorized Execution: Optimizing Analytical and Semantic Queries over RelationsRelated / background paper · 2026-09-08Affiliation source: Polytechnique Montréal
• Beyond Quacking: Deep Integration of Language Models and RAG into DuckDBCore SQPE paper · 2025-04-01Affiliation source: Polytechnique Montréal

Coauthors in this collection: Anas Dorbani, Sunny Yasser, Jimmy Lin.

• Text2SQL is Not Enough: Unifying AI and Databases with TAGRelated / background paper · 2024-08-27Affiliation source: UC Berkeley
• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: UC Berkeley

Coauthors in this collection: Shu Liu, Asim Biswal, Audrey Cheng, Luis Gaspar Schroeder, Liana Patel, Shiyi Cao, Xiangxi Mo, Ion Stoica, Joseph E. Gonzalez, Matei Zaharia, Siddarth Jha, Carlos Guestrin.

• Access Paths for Efficient Ordering with Large Language ModelsCore SQPE paper · 2025-08-30Affiliation source: UC Santa Barbara
• Hybrid Querying Over Relational Databases and Large Language ModelsRelated / background paper · 2024-08-01Affiliation source: UC Santa Barbara

Coauthors in this collection: Fuheng Zhao, Jiayue Chen, Yiming Pan, Tahseen Rabbani, Sohaib, Divyakant Agrawal, Paritosh Aggarwal, Anupam Datta, Dimitris Tsirogiannis.

• Factorized and Vectorized Execution: Optimizing Analytical and Semantic Queries over RelationsRelated / background paper · 2026-09-08Affiliation source: Polytechnique Montréal
• Beyond Quacking: Deep Integration of Language Models and RAG into DuckDBCore SQPE paper · 2025-04-01Affiliation source: Polytechnique Montréal

Coauthors in this collection: Sunny Yasser, Jimmy Lin, Amine Mhedhbi.

• Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase MethodCore SQPE paper · 2026-06-06Affiliation source: EPFL

Coauthors in this collection: Kyoungmin Kim, Martin Catheland.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: University of Technology Nuremberg

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Immanuel Trummer.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: University of Technology Nuremberg

Coauthors in this collection: Jiale Lao, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer.

• Text2SQL is Not Enough: Unifying AI and Databases with TAGRelated / background paper · 2024-08-27Affiliation source: UC Berkeley
• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: UC Berkeley

Coauthors in this collection: Shu Liu, Amog Kamsetty, Audrey Cheng, Luis Gaspar Schroeder, Liana Patel, Shiyi Cao, Xiangxi Mo, Ion Stoica, Joseph E. Gonzalez, Matei Zaharia, Siddarth Jha, Carlos Guestrin.

• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: UC Berkeley

Coauthors in this collection: Shu Liu, Asim Biswal, Amog Kamsetty, Luis Gaspar Schroeder, Liana Patel, Shiyi Cao, Xiangxi Mo, Ion Stoica, Joseph E. Gonzalez, Matei Zaharia.

• UQE: A Query Engine for Unstructured DatabasesCore SQPE paper · 2024-06-23Affiliation source: Google

Coauthors in this collection: Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Bo Dai, Sherry Yang, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans.

• UQE: A Query Engine for Unstructured DatabasesCore SQPE paper · 2024-06-23Affiliation source: Google

Coauthors in this collection: Hanjun Dai, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans.

• Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL QueriesCore SQPE paper · 2025-06-29Affiliation source: Peking University

Coauthors in this collection: Zhengren Wang, Dongwen Yao, Bozhou Li, Dongsheng Ma, Bo Li, Zhiyu Li, Feiyu Xiong, Linpeng Tang, Wentao Zhang.

• SemReuse: Certified Reuse of Cached Natural-Language Views for Semantic OperatorsCore SQPE paper · 2026-10-12Affiliation source: East China Normal University

Coauthors in this collection: Phat T. Tran-Truong, Tung Kieu, Xuan-Bach Le, Son X. Ha, Duc Kieu, Christian S. Jensen.

• UQE: A Query Engine for Unstructured DatabasesCore SQPE paper · 2024-06-23Affiliation source: Google · Georgia Institute of Technology

Coauthors in this collection: Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans.

• Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL QueriesCore SQPE paper · 2025-06-29Affiliation source: Peking University

Coauthors in this collection: Zhengren Wang, Dongwen Yao, Bozhou Li, Dongsheng Ma, Zhiyu Li, Feiyu Xiong, Bin Cui, Linpeng Tang, Wentao Zhang.

• Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and AnalysisCore SQPE paper · 2026-03-03Affiliation source: Alibaba Group
• UniDM: A Unified Framework for Data Manipulation with Large Language ModelsRelated / background paper · 2024-05-10Affiliation source: Alibaba Group

Coauthors in this collection: Yunxiang Su, Tianjing Zeng, Zhongjun Ding, Yin Lin, Rong Zhu, Zhewei Wei, Jingren Zhou, Yichen Qian, Yongyi He, Jintao Huang, Zhijian Ma, Haibin Wang, Yaohua Wang, Xiuyu Sun, Defu Lian.

• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Paweł Liskowski, Benjamin Han, Paritosh Aggarwal, Boxin Jiang, Nitish Jindal, Zihan Li, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Anupam Datta, Nathan Wiegand, Dimitris Tsirogiannis.

• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Paweł Liskowski, Benjamin Han, Paritosh Aggarwal, Bowei Chen, Nitish Jindal, Zihan Li, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Anupam Datta, Nathan Wiegand, Dimitris Tsirogiannis.

• Benchmarking Hybrid Deep Research Across Database Querying and Web SearchCore SQPE paper · 2026-09-08Affiliation source: Snowflake

Coauthors in this collection: Ruofan Wu, Peiran Xu, Xiaolong Li, Fan Shu, Soyoung Yoon, Yite Wang, Xiaodong Yu, Feng Yan, Debiao Li, Yuxiong He, Zhewei Yao.

• Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL QueriesCore SQPE paper · 2025-06-29Affiliation source: Peking University

Coauthors in this collection: Zhengren Wang, Dongwen Yao, Dongsheng Ma, Bo Li, Zhiyu Li, Feiyu Xiong, Bin Cui, Linpeng Tang, Wentao Zhang.

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsCore SQPE paper · 2026-07-07Affiliation source: Snowflake
• ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column ExplorationRelated / background paper · 2025-02-02Affiliation source: Snowflake

Coauthors in this collection: Tianyang Liu, Fangyu Lei, Nikki Lijing Kuang, Jixuan Chen, Tao Yu, Julian McAuley, Zhewei Yao, Yuxiong He, Minghang Deng, Ashwin Ramachandran, Lanxiang Hu, Anupam Datta, Hao Zhang.

• Text2SQL is Not Enough: Unifying AI and Databases with TAGRelated / background paper · 2024-08-27Affiliation source: Stanford University
• Semantic Operators: A Declarative Model for Rich, AI-based Data ProcessingCore SQPE paper · 2024-07-16Affiliation source: Stanford University

Coauthors in this collection: Liana Patel, Siddharth Jha, Melissa Pan, Harshit Gupta, Parth Asawa, Matei Zaharia, Asim Biswal, Siddarth Jha, Amog Kamsetty, Shu Liu, Joseph E. Gonzalez.

• UQE: A Query Engine for Unstructured DatabasesCore SQPE paper · 2024-06-23Affiliation source: Google

Coauthors in this collection: Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Dale Schuurmans.

• SUQL: Conversational Search over Structured and Unstructured Data with Large Language ModelsCore SQPE paper · 2023-11-16Affiliation source: Stanford University

Coauthors in this collection: Shicheng Liu, Jialiang Xu, Wesley Tjangnaka, Sina J. Semnani, Monica S. Lam.

• Unstructured Data Analysis using LLMs: A Comprehensive BenchmarkCore SQPE paper · 2025-10-31Affiliation source: Beijing Institute of Technology
• QUEST: Query Optimization in Unstructured Document AnalysisRelated / background paper · 2025-07-09Affiliation source: Beijing Institute of Technology

Coauthors in this collection: Qiyan Deng, Jianhui Li, Jinqi Liu, Junzhi She, Kaisen Jin, Zhaoze Sun, Yuhao Deng, Jia Yuan, Ye Yuan, Guoren Wang, Lei Cao, Xinyu Guo, Han Han.

• SemReuse: Certified Reuse of Cached Natural-Language Views for Semantic OperatorsCore SQPE paper · 2026-10-12Affiliation source: Aalborg University

Coauthors in this collection: Phat T. Tran-Truong, Tung Kieu, Xuan-Bach Le, Son X. Ha, Duc Kieu, Bin Yang.

• SemJoin: Semantic Join OptimizationCore SQPE paper · 2026-06-28Affiliation source: Purdue University

Coauthors in this collection: Aditya Banerjee, Jiaxuan Wang, Chunwei Liu.

• NousDB - A Fast Query Engine for Semantic AnalyticsCore SQPE paper · 2026-10-20Affiliation source: National and Kapodistrian University of Athens · Athena Research Center

Coauthors in this collection: Georgia Koutrika, Yannis Ioannidis.

• Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal DataCore SQPE paper · 2026-02-02Affiliation source: University of Florida
• The MADlib analytics library: or MAD skills, the SQLRelated / background paper · 2012-08Affiliation source: U. Florida

Coauthors in this collection: Ruyu Li, Tinghui Zhang, Haodi Ma, Yifan Wang, Joseph M. Hellerstein, Christoper Ré, Florian Schoppmann, Eugene Fratkin, Aleksander Gorajek, Kee Siong Ng, Caleb Welton, Xixuan Feng, Kun Li, Arun Kumar.

• UQE: A Query Engine for Unstructured DatabasesCore SQPE paper · 2024-06-23Affiliation source: Google · University of Alberta

Coauthors in this collection: Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton.

• Benchmarking Hybrid Deep Research Across Database Querying and Web SearchCore SQPE paper · 2026-09-08Affiliation source: UCLA

Coauthors in this collection: Ruofan Wu, Peiran Xu, Xiaolong Li, Fan Shu, Soyoung Yoon, Yite Wang, Xiaodong Yu, Boyi Liu, Feng Yan, Yuxiong He, Zhewei Yao.

• Access Paths for Efficient Ordering with Large Language ModelsCore SQPE paper · 2025-08-30Affiliation source: UC Santa Barbara
• Hybrid Querying Over Relational Databases and Large Language ModelsRelated / background paper · 2024-08-01Affiliation source: UC Santa Barbara

Coauthors in this collection: Fuheng Zhao, Jiayue Chen, Yiming Pan, Tahseen Rabbani, Sohaib, Amr El Abbadi, Paritosh Aggarwal, Anupam Datta, Dimitris Tsirogiannis.

• Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL QueriesCore SQPE paper · 2025-06-29Affiliation source: Peking University

Coauthors in this collection: Zhengren Wang, Dongwen Yao, Bozhou Li, Bo Li, Zhiyu Li, Feiyu Xiong, Bin Cui, Linpeng Tang, Wentao Zhang.

• Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL QueriesCore SQPE paper · 2025-06-29Affiliation source: Shanghai Jiao Tong University

Coauthors in this collection: Zhengren Wang, Bozhou Li, Dongsheng Ma, Bo Li, Zhiyu Li, Feiyu Xiong, Bin Cui, Linpeng Tang, Wentao Zhang.

• Sema: A High-performance System for LLM-based Semantic Query ProcessingCore SQPE paper · 2026-03-12Affiliation source: Wuhan University

Coauthors in this collection: Kangkang Qi, Wenbo Li, Hao Zhang, Yuanyuan Zhu, Jeffrey Xu Yu, Kangfei Zhao.

• SemReuse: Certified Reuse of Cached Natural-Language Views for Semantic OperatorsCore SQPE paper · 2026-10-12Affiliation source: Deakin University

Coauthors in this collection: Phat T. Tran-Truong, Tung Kieu, Xuan-Bach Le, Son X. Ha, Bin Yang, Christian S. Jensen.

• DocETL: Agentic Query Rewriting and Evaluation for Complex Document ProcessingCore SQPE paper · 2024-10-16Affiliation source: Columbia University
• Relationalizing Tables with Large Language Models: The Promise and ChallengesRelated / background paper · 2024-05-13Affiliation source: DSI, Columbia University,New York,United States

Coauthors in this collection: Shreya Shankar, Tristan Chambers, Tarak Shah, Aditya G. Parameswaran, Zezhou Huang.

• Benchmarking Hybrid Deep Research Across Database Querying and Web SearchCore SQPE paper · 2026-09-08Affiliation source: University of Houston

Coauthors in this collection: Ruofan Wu, Peiran Xu, Xiaolong Li, Soyoung Yoon, Yite Wang, Xiaodong Yu, Boyi Liu, Feng Yan, Debiao Li, Yuxiong He, Zhewei Yao.

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsCore SQPE paper · 2026-07-07Affiliation source: University of Hong Kong
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL WorkflowsRelated / background paper · 2024-11-12Affiliation source: University of Hong Kong

Coauthors in this collection: Tianyang Liu, Canwen Xu, Nikki Lijing Kuang, Jixuan Chen, Tao Yu, Julian McAuley, Zhewei Yao, Yuxiong He, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang.

• Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL QueriesCore SQPE paper · 2025-06-29Affiliation source: Institute for Advanced Algorithms Research, Shanghai

Coauthors in this collection: Zhengren Wang, Dongwen Yao, Bozhou Li, Dongsheng Ma, Bo Li, Zhiyu Li, Bin Cui, Linpeng Tang, Wentao Zhang.

• Benchmarking Hybrid Deep Research Across Database Querying and Web SearchCore SQPE paper · 2026-09-08Affiliation source: University of Houston

Coauthors in this collection: Ruofan Wu, Peiran Xu, Xiaolong Li, Fan Shu, Soyoung Yoon, Yite Wang, Xiaodong Yu, Boyi Liu, Debiao Li, Yuxiong He, Zhewei Yao.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: Google

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer.

• NousDB - A Fast Query Engine for Semantic AnalyticsCore SQPE paper · 2026-10-20Affiliation source: Athena Research Center

Coauthors in this collection: Christos Tsapelas, Yannis Ioannidis.

• Unstructured Data Analysis using LLMs: A Comprehensive BenchmarkCore SQPE paper · 2025-10-31Affiliation source: Beijing Institute of Technology
• QUEST: Query Optimization in Unstructured Document AnalysisRelated / background paper · 2025-07-09Affiliation source: Beijing Institute of Technology

Coauthors in this collection: Qiyan Deng, Jianhui Li, Chengliang Chai, Jinqi Liu, Junzhi She, Kaisen Jin, Zhaoze Sun, Yuhao Deng, Jia Yuan, Ye Yuan, Lei Cao, Xinyu Guo, Han Han.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: University of Michigan

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer.

• PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query PlansCore SQPE paper · 2026-04-10Affiliation source: UC Berkeley

Coauthors in this collection: Qiuyang Mang, Yufan Xiang, Hangrui Zhou, Runyuan He, Jiaxiang Yu, Aditya G. Parameswaran, Alvin Cheung.

• Demo of SemWeave: Semantic Common Expressions for LLM-powered Query ProcessingCore SQPE paper · 2026-05-30Affiliation source: Microsoft Gray Systems Lab, Redmond, WA, USA

Coauthors in this collection: Md. Tareq Mahmood, Venkatesh Emani, Shivaram Venkataraman.

• PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query PlansCore SQPE paper · 2026-04-10Affiliation source: UC Berkeley

Coauthors in this collection: Qiuyang Mang, Yufan Xiang, Runyuan He, Jiaxiang Yu, Hanchen Li, Aditya G. Parameswaran, Alvin Cheung.

• UQE: A Query Engine for Unstructured DatabasesCore SQPE paper · 2024-06-23Affiliation source: Google

Coauthors in this collection: Bethany Yixin Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans.

• Prune First, Decide Fast: Scalable Semantic Query Processing with JEVDBCore SQPE paper · 2026-10-01Affiliation source: Purdue University

Coauthors in this collection: Zhengle Wang, Fuheng Zhao, Chunwei Liu.

• Sema: A High-performance System for LLM-based Semantic Query ProcessingCore SQPE paper · 2026-03-12Affiliation source: The Chinese University of Hong Kong

Coauthors in this collection: Kangkang Qi, Dongyang Xie, Wenbo Li, Yuanyuan Zhu, Jeffrey Xu Yu, Kangfei Zhao.

• Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal DataCore SQPE paper · 2026-02-02Affiliation source: University of Florida

Coauthors in this collection: Ruyu Li, Tinghui Zhang, Daisy Zhe Wang, Yifan Wang.

• Semantic Operators: A Declarative Model for Rich, AI-based Data ProcessingCore SQPE paper · 2024-07-16Affiliation source: Stanford University

Coauthors in this collection: Liana Patel, Siddharth Jha, Melissa Pan, Parth Asawa, Carlos Guestrin, Matei Zaharia.

• Kalypso: Relational LLM ServingCore SQPE paper · 2026-07-26Affiliation source: University of Massachusetts Amherst

Coauthors in this collection: Md Ashraful Islam, Huy Gia Cao, Hui Guan, Marco Serafini.

• Kalypso: Relational LLM ServingCore SQPE paper · 2026-07-26Affiliation source: University of Massachusetts Amherst

Coauthors in this collection: Hojae Son, Md Ashraful Islam, Huy Gia Cao, Marco Serafini.

• Kalypso: Relational LLM ServingCore SQPE paper · 2026-07-26Affiliation source: University of Massachusetts Amherst

Coauthors in this collection: Hojae Son, Md Ashraful Islam, Hui Guan, Marco Serafini.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: Cornell University
• Implementing Semantic Join Operators EfficientlyRelated / background paper · 2025-10-09Affiliation source: Cornell University
• ThalamusDB: Approximate Query Processing on Multi-Modal DataRelated / background paper · 2024-05-29Affiliation source: Cornell University, Ithaca, NY, USA
• Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data LakesRelated / background paper · 2023-04-19Affiliation source: Cornell University

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Saehan Jo, Simran Arora, Brandon Yang, Sabri Eyuboglu, Avanika Narayan, Andrew Hojel, Christopher Ré.

• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: UC Berkeley
• SGLang: Efficient Execution of Structured Language Model ProgramsRelated / background paper · 2023-12-12Affiliation source: UC Berkeley
• Efficient Memory Management for Large Language Model Serving with PagedAttentionRelated / background paper · 2023-09-12Affiliation source: UC Berkeley

Coauthors in this collection: Shu Liu, Asim Biswal, Amog Kamsetty, Audrey Cheng, Luis Gaspar Schroeder, Liana Patel, Shiyi Cao, Xiangxi Mo, Joseph E. Gonzalez, Matei Zaharia, Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Hao Zhang, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Christos Kozyrakis, Clark Barrett.

• CADENZA: Compiling Natural-Language Intent into Task-Specific Operator DAGs for Semantic Query ProcessingCore SQPE paper · 2026-06-28Affiliation source: POSTECH

Coauthors in this collection: Yongjoo Park, Wook-Shin Han.

• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Paweł Liskowski, Benjamin Han, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Nitish Jindal, Zihan Li, Aaron Lin, Kyle Schmaus, Weicheng Zhao, Anupam Datta, Nathan Wiegand, Dimitris Tsirogiannis.

• Sema: A High-performance System for LLM-based Semantic Query ProcessingCore SQPE paper · 2026-03-12Affiliation source: HKUST (Guangzhou)
• Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter ParadigmRelated / background paper · 2026-03-05Affiliation source: HKUST (Guangzhou)

Coauthors in this collection: Kangkang Qi, Dongyang Xie, Wenbo Li, Hao Zhang, Yuanyuan Zhu, Kangfei Zhao, Nan Hou, Jiadong Xie.

• Unstructured Data Analysis using LLMs: A Comprehensive BenchmarkCore SQPE paper · 2025-10-31Affiliation source: University of Arizona

Coauthors in this collection: Qiyan Deng, Jianhui Li, Chengliang Chai, Jinqi Liu, Junzhi She, Kaisen Jin, Zhaoze Sun, Yuhao Deng, Ye Yuan, Guoren Wang, Lei Cao.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: Cornell University

Coauthors in this collection: Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer.

• SUQL: Conversational Search over Structured and Unstructured Data with Large Language ModelsCore SQPE paper · 2023-11-16Affiliation source: Stanford University

Coauthors in this collection: Shicheng Liu, Wesley Tjangnaka, Sina J. Semnani, Chen Jie Yu, Monica S. Lam.

• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]Core SQPE paper · 2026-05-18Affiliation source: Google

Coauthors in this collection: Yeounoh Chung, Rushabh Desai, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Khadilkar, Xianshun Chen, Sam Idicula, Fatma Özcan, Alon Halevy, Yannis Papakonstantinou.

• Unstructured Data Analysis using LLMs: A Comprehensive BenchmarkCore SQPE paper · 2025-10-31Affiliation source: Beijing Institute of Technology

Coauthors in this collection: Qiyan Deng, Chengliang Chai, Jinqi Liu, Junzhi She, Kaisen Jin, Zhaoze Sun, Yuhao Deng, Jia Yuan, Ye Yuan, Guoren Wang, Lei Cao.

• PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query PlansCore SQPE paper · 2026-04-10Affiliation source: UC Berkeley

Coauthors in this collection: Qiuyang Mang, Yufan Xiang, Hangrui Zhou, Runyuan He, Hanchen Li, Aditya G. Parameswaran, Alvin Cheung.

• SemJoin: Semantic Join OptimizationCore SQPE paper · 2026-06-28Affiliation source: Purdue University

Coauthors in this collection: Christopher Gou, Aditya Banerjee, Chunwei Liu.

• Access Paths for Efficient Ordering with Large Language ModelsCore SQPE paper · 2025-08-30Affiliation source: University of Chicago

Coauthors in this collection: Fuheng Zhao, Yiming Pan, Tahseen Rabbani, Sohaib, Divyakant Agrawal, Amr El Abbadi, Paritosh Aggarwal, Anupam Datta, Dimitris Tsirogiannis.

• RankLLM: A Python Package for Reranking with LLMsRelated / background paper · 2025-05-25Affiliation source: University of Waterloo
• Beyond Quacking: Deep Integration of Language Models and RAG into DuckDBCore SQPE paper · 2025-04-01Affiliation source: University of Waterloo
• RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!Related / background paper · 2023-12-05Affiliation source: University of Waterloo

Coauthors in this collection: Anas Dorbani, Sunny Yasser, Amine Mhedhbi, Sahel Sharifymoghaddam, Ronak Pradeep, Andre Slavescu, Ryan Nguyen, Andrew Xu, Zijian Chen, Yilin Zhang, Yidi Chen, Jasper Xian.

• Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and AnalysisCore SQPE paper · 2026-03-03Affiliation source: Alibaba Group
• UniDM: A Unified Framework for Data Manipulation with Large Language ModelsRelated / background paper · 2024-05-10Affiliation source: Alibaba Group

Coauthors in this collection: Yunxiang Su, Tianjing Zeng, Zhongjun Ding, Yin Lin, Rong Zhu, Zhewei Wei, Bolin Ding, Yichen Qian, Yongyi He, Jintao Huang, Zhijian Ma, Haibin Wang, Yaohua Wang, Xiuyu Sun, Defu Lian.

• Unstructured Data Analysis using LLMs: A Comprehensive BenchmarkCore SQPE paper · 2025-10-31Affiliation source: Beijing Institute of Technology

Coauthors in this collection: Qiyan Deng, Jianhui Li, Chengliang Chai, Junzhi She, Kaisen Jin, Zhaoze Sun, Yuhao Deng, Jia Yuan, Ye Yuan, Guoren Wang, Lei Cao.

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsCore SQPE paper · 2026-07-07Affiliation source: UC San Diego
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL WorkflowsRelated / background paper · 2024-11-12Affiliation source: University of Hong Kong

Coauthors in this collection: Tianyang Liu, Canwen Xu, Fangyu Lei, Nikki Lijing Kuang, Tao Yu, Julian McAuley, Zhewei Yao, Yuxiong He, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang.

• Text2SQL is Not Enough: Unifying AI and Databases with TAGRelated / background paper · 2024-08-27Affiliation source: UC Berkeley
• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: UC Berkeley
• SGLang: Efficient Execution of Structured Language Model ProgramsRelated / background paper · 2023-12-12Affiliation source: UC Berkeley
• Efficient Memory Management for Large Language Model Serving with PagedAttentionRelated / background paper · 2023-09-12Affiliation source: UC Berkeley

Coauthors in this collection: Shu Liu, Asim Biswal, Amog Kamsetty, Audrey Cheng, Luis Gaspar Schroeder, Liana Patel, Shiyi Cao, Xiangxi Mo, Ion Stoica, Matei Zaharia, Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Hao Zhang, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Christos Kozyrakis, Clark Barrett, Siddarth Jha, Carlos Guestrin.

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsCore SQPE paper · 2026-07-07Affiliation source: UC San Diego

Coauthors in this collection: Tianyang Liu, Canwen Xu, Fangyu Lei, Nikki Lijing Kuang, Jixuan Chen, Tao Yu, Zhewei Yao, Yuxiong He.

• Unstructured Data Analysis using LLMs: A Comprehensive BenchmarkCore SQPE paper · 2025-10-31Affiliation source: Beijing Institute of Technology

Coauthors in this collection: Qiyan Deng, Jianhui Li, Chengliang Chai, Jinqi Liu, Kaisen Jin, Zhaoze Sun, Yuhao Deng, Jia Yuan, Ye Yuan, Guoren Wang, Lei Cao.

• Unstructured Data Analysis using LLMs: A Comprehensive BenchmarkCore SQPE paper · 2025-10-31Affiliation source: Beijing Institute of Technology
• QUEST: Query Optimization in Unstructured Document AnalysisRelated / background paper · 2025-07-09Affiliation source: Beijing Institute of Technology

Coauthors in this collection: Qiyan Deng, Jianhui Li, Chengliang Chai, Jinqi Liu, Junzhi She, Zhaoze Sun, Yuhao Deng, Jia Yuan, Ye Yuan, Guoren Wang, Lei Cao, Xinyu Guo, Han Han.

• Sema: A High-performance System for LLM-based Semantic Query ProcessingCore SQPE paper · 2026-03-12Affiliation source: Beijing Institute of Technology
• Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter ParadigmRelated / background paper · 2026-03-05Affiliation source: Beijing Institute of Technology

Coauthors in this collection: Kangkang Qi, Dongyang Xie, Wenbo Li, Hao Zhang, Yuanyuan Zhu, Jeffrey Xu Yu, Nan Hou, Jiadong Xie.

• Sema: A High-performance System for LLM-based Semantic Query ProcessingCore SQPE paper · 2026-03-12Affiliation source: Beijing Institute of Technology

Coauthors in this collection: Dongyang Xie, Wenbo Li, Hao Zhang, Yuanyuan Zhu, Jeffrey Xu Yu, Kangfei Zhao.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: Google

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Sebastian Schelter, Andreas Kipf, Immanuel Trummer.

• Streaming Model Cascades for Semantic SQLRelated / background paper · 2026-04-01Affiliation source: Snowflake
• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Paweł Liskowski, Benjamin Han, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Nitish Jindal, Zihan Li, Aaron Lin, Jay Tayade, Weicheng Zhao, Anupam Datta, Nathan Wiegand, Dimitris Tsirogiannis.

• Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase MethodCore SQPE paper · 2026-06-06Affiliation source: EPFL

Coauthors in this collection: Martin Catheland, Anastasia Ailamaki.

• Multi-Objective Agentic Rewrites for Unstructured Data ProcessingCore SQPE paper · 2025-12-02Affiliation source: University of Washington

Coauthors in this collection: Shreya Shankar, Sepanta Zeighami, Yeounoh Chung, Fatma Özcan, Aditya G. Parameswaran.

• Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL QueriesCore SQPE paper · 2025-06-29Affiliation source: OriginHub Technology · Institute for Advanced Algorithms Research, Shanghai

Coauthors in this collection: Zhengren Wang, Dongwen Yao, Bozhou Li, Dongsheng Ma, Bo Li, Zhiyu Li, Feiyu Xiong, Bin Cui, Wentao Zhang.

• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: UC Berkeley · Technical University of Munich

Coauthors in this collection: Shu Liu, Asim Biswal, Amog Kamsetty, Audrey Cheng, Liana Patel, Shiyi Cao, Xiangxi Mo, Ion Stoica, Joseph E. Gonzalez, Matei Zaharia.

• Kalypso: Relational LLM ServingCore SQPE paper · 2026-07-26Affiliation source: University of Massachusetts Amherst

Coauthors in this collection: Hojae Son, Md Ashraful Islam, Huy Gia Cao, Hui Guan.

• Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase MethodCore SQPE paper · 2026-06-06Affiliation source: EPFL

Coauthors in this collection: Kyoungmin Kim, Anastasia Ailamaki.

• Kalypso: Relational LLM ServingCore SQPE paper · 2026-07-26Affiliation source: University of Massachusetts Amherst

Coauthors in this collection: Hojae Son, Huy Gia Cao, Hui Guan, Marco Serafini.

• Demo of SemWeave: Semantic Common Expressions for LLM-powered Query ProcessingCore SQPE paper · 2026-05-30Affiliation source: University of Wisconsin-Madison, Madison, WI, USA

Coauthors in this collection: Venkatesh Emani, Hangdong Zhao, Shivaram Venkataraman.

• Semantic Operators: A Declarative Model for Rich, AI-based Data ProcessingCore SQPE paper · 2024-07-16Affiliation source: UC Berkeley

Coauthors in this collection: Liana Patel, Siddharth Jha, Harshit Gupta, Parth Asawa, Carlos Guestrin, Matei Zaharia.

• Abacus: A Cost-Based Optimizer for Semantic Operator SystemsRelated / background paper · 2025-05-20Affiliation source: MIT
• BEAVER: An Enterprise Benchmark for Text-to-SQLRelated / background paper · 2024-09-03Affiliation source: MIT
• A Declarative System for Optimizing AI WorkloadsCore SQPE paper · 2024-05-23Affiliation source: MIT

Coauthors in this collection: Chunwei Liu, Matthew Russo, Lei Cao, Peter Baille Chen, Zui Chen, Michael Franklin, Tim Kraska, Samuel Madden, Gerardo Vitagliano, Sivaprasad Sudhir, Peter Baile Chen, Devin Yang, Weiyue Li, Fabian Wenz, Yi Zhang, Nesime Tatbul, Çağatay Demiralp, Michael Stonebraker.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: Vrije Universiteit Amsterdam

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer.

• A Declarative System for Optimizing AI WorkloadsCore SQPE paper · 2024-05-23Affiliation source: University of Chicago

Coauthors in this collection: Chunwei Liu, Matthew Russo, Michael Cafarella, Lei Cao, Peter Baille Chen, Zui Chen, Tim Kraska, Samuel Madden, Gerardo Vitagliano.

• SUQL: Conversational Search over Structured and Unstructured Data with Large Language ModelsCore SQPE paper · 2023-11-16Affiliation source: Stanford University

Coauthors in this collection: Shicheng Liu, Jialiang Xu, Wesley Tjangnaka, Sina J. Semnani, Chen Jie Yu.

• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Paweł Liskowski, Benjamin Han, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Nitish Jindal, Zihan Li, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Anupam Datta, Dimitris Tsirogiannis.

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsCore SQPE paper · 2026-07-07Affiliation source: Snowflake

Coauthors in this collection: Tianyang Liu, Canwen Xu, Fangyu Lei, Jixuan Chen, Tao Yu, Julian McAuley, Zhewei Yao, Yuxiong He.

• Cortex AISQL: A Production SQL Engine for Unstructured DataCore SQPE paper · 2025-11-10Affiliation source: Snowflake

Coauthors in this collection: Paweł Liskowski, Benjamin Han, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Zihan Li, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Anupam Datta, Nathan Wiegand, Dimitris Tsirogiannis.

• SemPipes -- Optimizable Semantic Data Operators for Tabular Machine Learning PipelinesRelated / background paper · 2026-02-04Affiliation source: BIFOLD · TU Berlin
• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: BIFOLD & TU Berlin

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer, Matthias Boehm.

• Semantic Operators: A Declarative Model for Rich, AI-based Data ProcessingCore SQPE paper · 2024-07-16Affiliation source: UC Berkeley

Coauthors in this collection: Liana Patel, Siddharth Jha, Melissa Pan, Harshit Gupta, Carlos Guestrin, Matei Zaharia.

• Benchmarking Hybrid Deep Research Across Database Querying and Web SearchCore SQPE paper · 2026-09-08Affiliation source: UCLA

Coauthors in this collection: Ruofan Wu, Xiaolong Li, Fan Shu, Soyoung Yoon, Yite Wang, Xiaodong Yu, Boyi Liu, Feng Yan, Debiao Li, Yuxiong He, Zhewei Yao.

• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL WorkflowsRelated / background paper · 2024-11-12Affiliation source: Google
• UQE: A Query Engine for Unstructured DatabasesCore SQPE paper · 2024-06-23Affiliation source: Google

Coauthors in this collection: Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans, Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, Tao Yu.

• The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI OperatorsCore SQPE paper · 2026-09-17Affiliation source: Google

Coauthors in this collection: Tarfah Alrashed, Fatma Özcan, Tal Neiman, Xianshun Chen.

• A Declarative System for Optimizing AI WorkloadsCore SQPE paper · 2024-05-23Affiliation source: MIT

Coauthors in this collection: Chunwei Liu, Matthew Russo, Michael Cafarella, Lei Cao, Zui Chen, Michael Franklin, Tim Kraska, Samuel Madden, Gerardo Vitagliano.

• SemReuse: Certified Reuse of Cached Natural-Language Views for Semantic OperatorsCore SQPE paper · 2026-10-12Affiliation source: Vietnam National University

Coauthors in this collection: Tung Kieu, Xuan-Bach Le, Son X. Ha, Duc Kieu, Bin Yang, Christian S. Jensen.

• UQE: A Query Engine for Unstructured DatabasesCore SQPE paper · 2024-06-23Affiliation source: Google

Coauthors in this collection: Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Bo Dai, Sherry Yang, Azade Nova, Pengcheng Yin, Charles Sutton, Dale Schuurmans.

• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]Core SQPE paper · 2026-05-18Affiliation source: Google

Coauthors in this collection: Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Xianshun Chen, Sam Idicula, Fatma Özcan, Alon Halevy, Yannis Papakonstantinou.

• Larch: Learned Query Optimization for Semantic PredicatesCore SQPE paper · 2026-06-06Affiliation source: Snowflake

Coauthors in this collection: Fuheng Zhao, Paweł Liskowski, Zihan Li, Benjamin Han, Varich Boonsanong, Dimitris Tsirogiannis, Anupam Datta.

• PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query PlansCore SQPE paper · 2026-04-10Affiliation source: UC Berkeley

Coauthors in this collection: Yufan Xiang, Hangrui Zhou, Runyuan He, Jiaxiang Yu, Hanchen Li, Aditya G. Parameswaran, Alvin Cheung.

• Unstructured Data Analysis using LLMs: A Comprehensive BenchmarkCore SQPE paper · 2025-10-31Affiliation source: Beijing Institute of Technology
• QUEST: Query Optimization in Unstructured Document AnalysisRelated / background paper · 2025-07-09Affiliation source: Beijing Institute of Technology

Coauthors in this collection: Jianhui Li, Chengliang Chai, Jinqi Liu, Junzhi She, Kaisen Jin, Zhaoze Sun, Yuhao Deng, Jia Yuan, Ye Yuan, Guoren Wang, Lei Cao, Xinyu Guo, Han Han.

• Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and AnalysisCore SQPE paper · 2026-03-03Affiliation source: Alibaba Group
• UniDM: A Unified Framework for Data Manipulation with Large Language ModelsRelated / background paper · 2024-05-10Affiliation source: Alibaba Group

Coauthors in this collection: Yunxiang Su, Tianjing Zeng, Zhongjun Ding, Yin Lin, Zhewei Wei, Bolin Ding, Jingren Zhou, Yichen Qian, Yongyi He, Jintao Huang, Zhijian Ma, Haibin Wang, Yaohua Wang, Xiuyu Sun, Defu Lian.

• PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query PlansCore SQPE paper · 2026-04-10Affiliation source: UC Berkeley

Coauthors in this collection: Qiuyang Mang, Yufan Xiang, Hangrui Zhou, Jiaxiang Yu, Hanchen Li, Aditya G. Parameswaran, Alvin Cheung.

• Benchmarking Hybrid Deep Research Across Database Querying and Web SearchCore SQPE paper · 2026-09-08Affiliation source: University of Houston

Coauthors in this collection: Peiran Xu, Xiaolong Li, Fan Shu, Soyoung Yoon, Yite Wang, Xiaodong Yu, Boyi Liu, Feng Yan, Debiao Li, Yuxiong He, Zhewei Yao.

• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]Core SQPE paper · 2026-05-18Affiliation source: Google

Coauthors in this collection: Yeounoh Chung, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Khadilkar, Xianshun Chen, Sam Idicula, Fatma Özcan, Alon Halevy, Yannis Papakonstantinou.

• Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal DataCore SQPE paper · 2026-02-02Affiliation source: University of Hawaii at Manoa

Coauthors in this collection: Tinghui Zhang, Haodi Ma, Daisy Zhe Wang, Yifan Wang.

• 100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]Core SQPE paper · 2026-05-18Affiliation source: Google

Coauthors in this collection: Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Khadilkar, Xianshun Chen, Fatma Özcan, Alon Halevy, Yannis Papakonstantinou.

• KEN: An Execution Engine for Unstructured Database SystemsRelated / background paper · 2026Affiliation source: MIT
• Abacus: A Cost-Based Optimizer for Semantic Operator SystemsRelated / background paper · 2025-05-20Affiliation source: MIT
• A Declarative System for Optimizing AI WorkloadsCore SQPE paper · 2024-05-23Affiliation source: MIT

Coauthors in this collection: Chunwei Liu, Matthew Russo, Michael Cafarella, Lei Cao, Peter Baille Chen, Zui Chen, Michael Franklin, Tim Kraska, Gerardo Vitagliano, Sivaprasad Sudhir, Ferdi Kossmann, Ziniu Wu, Alex Turk, Nesime Tatbul.

• SemPipes -- Optimizable Semantic Data Operators for Tabular Machine Learning PipelinesRelated / background paper · 2026-02-04Affiliation source: BIFOLD · TU Berlin
• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: BIFOLD & TU Berlin

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Tianji Cong, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Andreas Kipf, Immanuel Trummer, Matthias Boehm.

• UQE: A Query Engine for Unstructured DatabasesCore SQPE paper · 2024-06-23Affiliation source: Google

Coauthors in this collection: Hanjun Dai, Bethany Yixin Wang, Xingchen Wan, Bo Dai, Azade Nova, Pengcheng Yin, Phitchaya Mangpo Phothilimthana, Charles Sutton, Dale Schuurmans.

• SUQL: Conversational Search over Structured and Unstructured Data with Large Language ModelsCore SQPE paper · 2023-11-16Affiliation source: Stanford University

Coauthors in this collection: Jialiang Xu, Wesley Tjangnaka, Sina J. Semnani, Chen Jie Yu, Monica S. Lam.

• Demo of SemWeave: Semantic Common Expressions for LLM-powered Query ProcessingCore SQPE paper · 2026-05-30Affiliation source: University of Wisconsin-Madison, Madison, WI, USA

Coauthors in this collection: Md. Tareq Mahmood, Venkatesh Emani, Hangdong Zhao.

• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: UC Berkeley
• SGLang: Efficient Execution of Structured Language Model ProgramsRelated / background paper · 2023-12-12Affiliation source: UC Berkeley

Coauthors in this collection: Shu Liu, Asim Biswal, Amog Kamsetty, Audrey Cheng, Luis Gaspar Schroeder, Liana Patel, Xiangxi Mo, Ion Stoica, Joseph E. Gonzalez, Matei Zaharia, Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Christos Kozyrakis, Clark Barrett, Ying Sheng.

• Text2SQL is Not Enough: Unifying AI and Databases with TAGRelated / background paper · 2024-08-27Affiliation source: UC Berkeley
• Optimizing LLM Queries in Relational Data Analytics WorkloadsCore SQPE paper · 2024-03-09Affiliation source: UC Berkeley

Coauthors in this collection: Asim Biswal, Amog Kamsetty, Audrey Cheng, Luis Gaspar Schroeder, Liana Patel, Shiyi Cao, Xiangxi Mo, Ion Stoica, Joseph E. Gonzalez, Matei Zaharia, Siddarth Jha, Carlos Guestrin.

• Semantic Operators: A Declarative Model for Rich, AI-based Data ProcessingCore SQPE paper · 2024-07-16Affiliation source: UC Berkeley

Coauthors in this collection: Liana Patel, Melissa Pan, Harshit Gupta, Parth Asawa, Carlos Guestrin, Matei Zaharia.

• SUQL: Conversational Search over Structured and Unstructured Data with Large Language ModelsCore SQPE paper · 2023-11-16Affiliation source: Stanford University

Coauthors in this collection: Shicheng Liu, Jialiang Xu, Wesley Tjangnaka, Chen Jie Yu, Monica S. Lam.

• Access Paths for Efficient Ordering with Large Language ModelsCore SQPE paper · 2025-08-30Affiliation source: UC Santa Barbara

Coauthors in this collection: Fuheng Zhao, Jiayue Chen, Yiming Pan, Tahseen Rabbani, Divyakant Agrawal, Amr El Abbadi, Paritosh Aggarwal, Anupam Datta, Dimitris Tsirogiannis.

• SemReuse: Certified Reuse of Cached Natural-Language Views for Semantic OperatorsCore SQPE paper · 2026-10-12Affiliation source: RMIT University

Coauthors in this collection: Phat T. Tran-Truong, Tung Kieu, Xuan-Bach Le, Duc Kieu, Bin Yang, Christian S. Jensen.

• Benchmarking Hybrid Deep Research Across Database Querying and Web SearchCore SQPE paper · 2026-09-08Affiliation source: Seoul National University

Coauthors in this collection: Ruofan Wu, Peiran Xu, Xiaolong Li, Fan Shu, Yite Wang, Xiaodong Yu, Boyi Liu, Feng Yan, Debiao Li, Yuxiong He, Zhewei Yao.

• Factorized and Vectorized Execution: Optimizing Analytical and Semantic Queries over RelationsRelated / background paper · 2026-09-08Affiliation source: Polytechnique Montréal
• Beyond Quacking: Deep Integration of Language Models and RAG into DuckDBCore SQPE paper · 2025-04-01Affiliation source: Polytechnique Montréal

Coauthors in this collection: Anas Dorbani, Jimmy Lin, Amine Mhedhbi.

• Access Paths for Efficient Ordering with Large Language ModelsCore SQPE paper · 2025-08-30Affiliation source: University of Chicago

Coauthors in this collection: Fuheng Zhao, Jiayue Chen, Yiming Pan, Sohaib, Divyakant Agrawal, Amr El Abbadi, Paritosh Aggarwal, Anupam Datta, Dimitris Tsirogiannis.

• The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI OperatorsCore SQPE paper · 2026-09-17Affiliation source: Google

Coauthors in this collection: Tarfah Alrashed, Fatma Özcan, Per Jacobsson, Xianshun Chen.

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsCore SQPE paper · 2026-07-07Affiliation source: University of Hong Kong
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL WorkflowsRelated / background paper · 2024-11-12Affiliation source: University of Hong Kong
• Binding Language Models in Symbolic LanguagesRelated / background paper · 2022-10-06Affiliation source: University of Hong Kong · University of Washington

Coauthors in this collection: Tianyang Liu, Canwen Xu, Fangyu Lei, Nikki Lijing Kuang, Jixuan Chen, Julian McAuley, Zhewei Yao, Yuxiong He, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith.

• DocETL: Agentic Query Rewriting and Evaluation for Complex Document ProcessingCore SQPE paper · 2024-10-16Affiliation source: BIDS Police Records Access Project

Coauthors in this collection: Shreya Shankar, Tristan Chambers, Aditya G. Parameswaran, Eugene Wu.

• The Stochastic Shift: A New Evaluation Paradigm for Text-to-SQL with AI OperatorsCore SQPE paper · 2026-09-17Affiliation source: Google

Coauthors in this collection: Fatma Özcan, Per Jacobsson, Tal Neiman, Xianshun Chen.

• SemBench: A Benchmark for Semantic Query Processing EnginesCore SQPE paper · 2025-11-03Affiliation source: University of Michigan

Coauthors in this collection: Jiale Lao, Andreas Zimmerer, Olga Ovcharenko, Matthew Russo, Gerardo Vitagliano, Michael Cochez, Fatma Özcan, Gautam Gupta, Thibaud Hottelier, H. V. Jagadish, Kris Kissel, Sebastian Schelter, Andreas Kipf, Immanuel Trummer.

• Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and AnalysisCore SQPE paper · 2026-03-03Affiliation source: Alibaba Group · Renmin University of China

Coauthors in this collection: Yunxiang Su, Zhongjun Ding, Yin Lin, Rong Zhu, Zhewei Wei, Bolin Ding, Jingren Zhou.

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL WorkflowsCore SQPE paper · 2026-07-07Affiliation source: UC San Diego

Coauthors in this collection: Canwen Xu, Fangyu Lei, Nikki Lijing Kuang, Jixuan Chen, Tao Yu, Julian McAuley, Zhewei Yao, Yuxiong He.

• Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven AnalyticsRelated / background paper · 2025-09-02Affiliation source: MIT
• Abacus: A Cost-Based Optimizer for Semantic Operator SystemsRelated / background paper · 2025-05-20Affiliation source: MIT
• A Declarative System for Optimizing AI WorkloadsCore SQPE paper · 2024-05-23Affiliation source: MIT