LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 11 days ago • 200
AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models Paper • 2607.02269 • Published 25 days ago • 9
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 252
Reflective Prompt Tuning through Language Model Function-Calling Paper • 2605.21781 • Published May 20 • 9