What Outcome RL Buys: Finishing, Reliability, Rarely Reach Paper • 2610.34894 • Published 28 days ago • 6
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence Paper • 2605.26340 • Published May 25 • 35
Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control Paper • 2603.09221 • Published Mar 10 • 1
Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning Paper • 2605.14040 • Published May 13 • 4
VLAP: Efficient Video-Language Alignment via Frame Prompting and Distilling for Video Question Answering Paper • 2312.08367 • Published Dec 13, 2023 • 1