ThinQuant: Scalable Rotation Learning for Weight and Activation Quantization of LLMsResearchSep 30, 2026
No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy DistillationResearchSep 30, 2026
A Unifying Framework of Concept-based Explainable AI with Completeness GuaranteesResearchSep 30, 2026
PADM\'E: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent EvaluatorsResearchSep 30, 2026