On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics Paper • 2609.35259 • Published 7 days ago • 175
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It Paper • 2609.36585 • Published 6 days ago • 70
Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models Paper • 2609.37568 • Published 6 days ago • 11
JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces Paper • 2610.00437 • Published 5 days ago • 7
Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration Paper • 2609.22753 • Published 9 days ago • 5
Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy Paper • 2609.34381 • Published 7 days ago • 7