Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL
Corentin Royer, Robin Oester, Yotam Perlitz +3
Text-to-SQL systems are typically trained and evaluated on a single dialect (SQLite), yet production deployments span PostgreSQL, MySQL, ClickHouse, and beyond. We show that this s…
cs.CL2025
Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models
Shien Zhu, Samuel Bohl, Robin Oester +1
Mixture-of-Experts (MoE) Large Language Models (LLMs) efficiently scale-up the model while keeping relatively low inference cost. As MoE models only activate part of the experts, r…