ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published 8 days ago • 30
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published 8 days ago • 30
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published 8 days ago • 30
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification Paper • 2603.15726 • Published Mar 16 • 186
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published 8 days ago • 30
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published 26 days ago • 48
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Paper • 2605.10434 • Published 16 days ago • 29
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Paper • 2605.10434 • Published 16 days ago • 29
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published 26 days ago • 48
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published 26 days ago • 48
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published 26 days ago • 48
MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents Paper • 2603.05697 • Published Mar 5