WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Paper • 2605.10434 • Published May 11 • 29
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published May 19 • 34
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published May 19 • 34
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published May 19 • 34
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification Paper • 2603.15726 • Published Mar 16 • 187
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published May 19 • 34
Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models Paper • 2602.01849 • Published Feb 2 • 5
AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis Paper • 2602.09372 • Published Feb 10 • 7
From Perception to Action: An Interactive Benchmark for Vision Reasoning Paper • 2602.21015 • Published Feb 24 • 24
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome Paper • 2603.28407 • Published Mar 30 • 72
MARS: Enabling Autoregressive Models Multi-Token Generation Paper • 2604.07023 • Published Apr 8 • 38
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published May 1 • 49
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Paper • 2605.10434 • Published May 11 • 29
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Paper • 2605.10434 • Published May 11 • 29
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published May 1 • 49
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published May 1 • 49
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published May 1 • 49
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling Paper • 2604.28185 • Published Apr 30 • 92
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling Paper • 2604.28185 • Published Apr 30 • 92