Click here to access the proceedings of the workshop.
Inferring Missing Data Lineage Links from Schema Metadata Using Transformer-Based Models
Maciej Brzeski (Jagiellonian University, Informatica); Adam Roman (Jagiellonian University)
TailorSQL: A NL2SQL System Tailored for Your Query Workload
Kapil Vaidya (Parallel Web Systems); Jialin Ding (Princeton University); Sebastian Kosak (Technical University of Munich); David Kernert (STACKIT); Chuan Lei (Amazon Web Services); Xiao Qin (Amazon Web Services); Abhinav Tripathy (Amazon Web Services); Ramesh Balan (Amazon Web Services); Balakrishnan Narayanaswamy (Amazon Web Services); Tim Kraska (Amazon Web Services)
Learning What Matters: Automated Feature Selection for Learned Cost Model in Parallel Stream Processing
Pratyush Agnihotri (TU Darmstadt); Carsten Binnig (TU Darmstadt and DFKI); Manisha Luthra (TU Darmstadt and DFKI)
AutoDebugger: Efficient Root Cause Analysis for Anomaly Jobs (Extended Abstract)
Fathelrahman Ali (Google); Yiwen Zhu (Microsoft); Lie Jiang (Microsoft); Zhen Li (Microsoft); Manting Li (Microsoft); Kun Huang (Microsoft); Lijing Lin (Microsoft); Long Tian (Microsoft); Xiaolei Liu (Microsoft); Subru Krishnan (Microsoft)
Grounding LLMs for Database Exploration: Intent Scoping and Paraphrasing for Robust NL2SQL
Catalina Dragusin (ETH Zurich); Katsiaryna Mirylenka (Zalando SE); Christoph Miksovic (IBM Research); Michael Glass (IBM Research); Nahuel Defosse (IBM Research); Paolo Scotton (IBM Research); Thomas Gschwind (IBM Research)
Instance-Optimized String Fingerprints (Extended Abstract)
Mihail Stoian (University of Technology Nuremberg); Johannes Thürauf (University of Technology Nuremberg); Andreas Zimmerer (University of Technology Nuremberg); Alexander van Renen (University of Technology Nuremberg); Andreas Kipf (University of Technology Nuremberg)
MageSQL: Enhancing In-context Learning for Text-to-SQL Applications with Large Language Models
Chen Shen (Megagon Labs); Jin Wang (Megagon Labs); Sajjadur Rahman (Adobe); Eser Kandogan (Megagon Labs)
JOB-Complex: A Challenging Benchmark for Traditional & Learned Query Optimization
Johannes Wehrstein (TU Darmstadt); Timo Eckmann (TU Darmstadt); Roman Heinrich (TU Darmstadt & DFKI); Carsten Binnig (TU Darmstadt & DFKI)
Bootstrapping Learned Cost Models with Synthetic SQL Queries (Extended Abstract)
Michael Nidd (IBM Research); Christoph Miksovic (IBM Research); Thomas Gschwind (IBM Research); Francesco Fusco (IBM Research); Andrea Giovannini (IBM Research); Ioana Giurgiu (IBM Research)
Exploring Wavelet Trees as Space-Efficient Physical-to-Sorted Mapping for Learned Indexes
Anwesha Saha (Boston University); Aneesh Raman (Boston University); Ryan Marcus (University of Pennsylvania); Manos Athanassoulis (Boston University)
Learning to Accelerate: Tuning Data Transfer Parameters
Benedikt Didrich (Technische Universität Berlin); Haralampos Gavriilidis (BIFOLD & Technische Universität Berlin); Vasilis Gkolemis (Athena Research Center); Matthias Boehm (BIFOLD & Technische Universität Berlin); Volker Markl (BIFOLD, Technische Universität Berlin & DFKI)
Research Challenges in Relational Database Management Systems for LLM Queries
Kerem Akillioglu (University of Waterloo)*; Anurag Chakraborty (University of Waterloo); Sairaj Voruganti (University of Waterloo); M. Tamer Özsu (University of Waterloo)