The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 3 days ago • 312
Nested Sparsity for Scalable Pretraining and Continual Learning Paper • 2610.31818 • Published 7 days ago • 12
Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks Paper • 2610.28889 • Published 9 days ago • 56
SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation Paper • 2610.16338 • Published 17 days ago • 7
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 21 days ago • 246
ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents Paper • 2610.13395 • Published 20 days ago • 56
A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning Paper • 2606.03335 • Published 23 days ago • 33
DecepEval: A Benchmark for Evaluating Deception in LLM Agents Paper • 2610.07967 • Published 23 days ago • 61
ProAR: Learning Prospective Reasoning with Autoregressive Video Models Paper • 2610.03664 • Published 27 days ago • 34
SenseNova-U1.5: Towards Native Unified Visual Intelligence Paper • 2609.11929 • Published Sep 10 • 174
Using Grounded Theory for Agent Behavior Analysis at Scale Paper • 2608.30391 • Published Aug 31 • 20
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? Paper • 2608.19799 • Published Aug 20 • 69