Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark Paper • 2510.13759 • Published 12 days ago • 9
VChain: Chain-of-Visual-Thought for Reasoning in Video Generation Paper • 2510.05094 • Published 21 days ago • 35
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning Paper • 2509.22576 • Published Sep 26 • 132
RecoWorld: Building Simulated Environments for Agentic Recommender Systems Paper • 2509.10397 • Published Sep 12 • 7