Stage-Level Executor Allocation in Apache Spark™ with Cost–Performance Trade-offs
Miriam Rateike (IBM, University of Tübingen); Isaac Waweru Wambugu, Celia Cintas, Michael Kaufmann, Ioana Giurgiu, Skyler Speakman (IBM)
Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for Database Bypass
Victor Giannakouris, Immanuel Trummer (Cornell University)
AI Query Compilation for Unified and Optimized Execution
Yeounoh Chung, Helena Caminal, Fatma Ozcan (Google)
Towards Practical Latency SLOs on Cloud Data Warehouses
Markos Markakis (MIT CSAIL); Tim Kraska (MIT CSAIL, G5 Labs)
Selectivity Estimation for Semantic Filters on Image Data
Matthias Urban, Vu Huy Nguyen (Technical University of Darmstadt); Gabriele Sanmartino, Paolo Papotti (EURECOM); Carsten Binnig (Technical University of Darmstadt, DFKI, Hessian AI)
MLSkip: Data Skipping for ML Filters via Lightweight Metadata
Mihail Stoian (University of Technology Nuremberg); Mark Gerarts (Hasselt University); Pascal Ginter (Technical University of Munich); Andreas Zimmerer (University of Technology Nuremberg); Jan Van den Bussche (Hasselt University); Andreas Kipf (University of Technology Nuremberg)
Bespoke-Card: Why Tune When You Can Generate? Synthesizing Workload-Specific Cardinality Estimators
Johannes Wehrstein, Anton Winter, Timo Eckmann (TU Darmstadt); Carsten Binnig (TU Darmstadt, DFKI, HessianAI)
Large Databases Need Small, Open-Weight Language Models
Parker Glenn, Alfy Samuel (Capital One)
Can Learned Query Optimizers Adapt Across DBMS Architectures? A Case Study with Balsa and DuckDB
Wangshu Hong, Ryan Marcus (University of Pennsylvania)
Two Surfaces of Ambiguity: Complementary Detection for Text-to-SQL
Leonhard Liu, Patrick K. Erdelt (Berliner Hochschule für Technik)
How Hard Can Indexing Be? Principled Dataset Hardness Measurement for Learned Indexes
Siyuan Zhang, Chuzhe Tang, Anastasia Ailamaki (EPFL)
Hollywood: Towards A Large Movie Dataset for Database Benchmarking
Ivan Iachnyk, Mihail Stoian, Andreas Kipf (University of Technology Nuremberg (UTN))
RUBICON: Agentic AI for Messy Enterprise Data
Fabian Wenz (TU Darmstadt and MIT); Felix Treutwein (Landeshauptstadt Muenchen); Çağatay Demiralp (AWS AI and MIT); Michael Stonebraker (MIT)
Generation of Adversarial Queries via Bayesian Optimization
Jeffrey Tao, Yimeng Zeng (University of Pennsylvania); Natalie Maus (Massachusetts Institute of Technology); Haydn Jones, Osbert Bastani, Jacob R. Gardner, Ryan Marcus (University of Pennsylvania)
ELT-Bench-Verified: Auditing Execution-Based Benchmarks for AI Data-Engineering Agents
Christopher Zanoli, Andrea Giovannini (IBM Research); Tengjun Jin (University of Illinois); Ana Klimovic (ETH Zurich); Yotam Perlitz (IBM Research)
Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints
Alan Gany (Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG); Bogdan Cautis (Singapore Institute of Technology); Silviu Maniu (Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG)
Metis: Machine learning based Dynamic Thread Control for High-Contention Transaction Processing
Sayaka Tayama, Tatsuhiro Nakamori, Hideyuki Kawashima (Keio University)