Session 1: LLMs for Databases
KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration
Waiting to Decompress: The Economics of LLM-Based Compression
Andreas Kipf, Tobias Schmidt, Ping-Lin Kuo, Skander Krid, Moritz Rengert, Luca Heller, Andreas Zimmerer, Mihail Stoian, Varun Pandey, Alexander van Renen
BridgeScope: A Universal Toolkit for Bridging Large Language Models and Databases
Lianggui Weng, Dandan Liu, Rong Zhu, Bolin Ding, Jingren Zhou
Making Prompts First-Class Citizens for Adaptive LLM Pipelines
Uğur Çetintemel, Shu Chen, Alexander W. Lee, Deepti Raghavan, Duo Lu, Andrew Crotty
Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics
Matthew Russo, Tim Kraska
Session 2: Data Platform Benchmarking and Optimization Techniques
End-to-End Declarative Data Analytics: Co-designing Engines, Interfaces, and Cloud Infrastructure
Pinghe Li, Tom Kuchler, Marko Kabić, Tobias Stocker, Gustavo Alonso, Ana Klimovic
Survivorship Bias in Industrial Database Workloads
Ryan Marcus, Jeffrey Tao, Peizhi Wu, Zijie Zhao
A Multi-tenant Relational OLTP Database at Salesforce
Vaibhav Arora, Subho Chatterjee, Terry Chong, Thomas Fanghaenel, Pat Helland, Jamie Martin, Kaushal Mittal, Nat Wyatt
I Can’t Believe It’s Not Yannakakis: Pragmatic Bitmap Filters in Microsoft SQL Server
Hangdong Zhao, Yuanyuan Tian, Rana Alotaibi, Bailu Ding, Nicolas Bruno, Jesús Camacho-Rodríguez, Vassilis Papadimos, Ernesto Cervantes Juárez, Cesar Galindo-Legaria, Carlo Curino
Fast Vector Search in PostgreSQL: A Decoupled Approach
Jiayi Liu, Yunan Zhang, Chenzhe Jin, Aditya Gupta, Shige Liu, Jianguo Wang
Session 3: Text-to-SQL, Agents, LLMs, Oh My!
Text-to-SQL Benchmarks are Broken: An In-Depth Analysis of Annotation Errors
Tengjun Jin, Yoojin Choi, Yuxuan Zhu, Daniel Kang
Leveraging Query Optimizers to Verify the Soundness of LLM-based Query Rewrites for Real-World Workloads, and More
Vivek Narasayya, Surajit Chaudhuri
BenchPress: A Human-in-the-Loop Annotation System for Rapid Text-to-SQL Benchmark Curation
Fabian Wenz, Omar Bouattour, Devin Yang, Justin Choi, Cecil Gregg, Nesime Tatbul, Çağatay Demiralp
Please Don’t Kill My Vibe: Empowering Agents with Data Flow Control
Charlie Summers, Haneen Mohammed, Eugene Wu
Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
Shu Liu, Soujanya Ponnapalli, Shreya Shankar, Sepanta Zeighami, Alan Zhu, Shubham Agarwal, Ruiqi Chen, Samion Suwito, Shuo Yuan, Ion Stoica, Matei Zaharia, Alvin Cheung, Natacha Crooks, Joseph E. Gonzalez, Aditya G. Parameswaran
Session 4: Distributed Coordination and Consistency
Consistency and Correctness in Data-Oriented Workflow Systems
Michael Stonebraker, Xinjing Zhou, Peter Kraft, Qian Li
Event Horizon: Asymmetric Dependencies for Fast Geo-Distributed Operations
Jonathan Arns, Harald Ng, Kyriakos Psarakis, Asterios Katsifodimos, Paris Carbone