Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization Paper • 2608.16072 • Published 9 days ago • 148
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published Jul 21 • 311
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published Jul 19 • 167
Motion4Motion: Motion Transfer Across Subjects at Inference Paper • 2607.11644 • Published Jul 13 • 13
LehongWu/grpo-fmb-qwen3_5_4b-oracle_all_512x1_prev_0710_0300-len_pen-s128_qwen35_122b_sft_ep2_0715 Updated Jul 16 • 1
HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents Paper • 2606.31179 • Published Jun 30 • 8
Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence Paper • 2605.30093 • Published May 28 • 15
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 253