Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model Paper • 2607.24904 • Published Jul 27 • 37
Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation Paper • 2608.08469 • Published Aug 9 • 2
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published Aug 26 • 174
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Paper • 2608.16320 • Published Aug 17 • 9
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Paper • 2608.16320 • Published Aug 17 • 9
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Paper • 2608.16320 • Published Aug 17 • 9
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing Paper • 2607.19064 • Published Jul 21 • 78
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Paper • 2605.10434 • Published May 11 • 30
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published May 19 • 31
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published May 19 • 31
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning Paper • 2605.20342 • Published May 19 • 31
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 • 31
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published May 1 • 47
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Paper • 2605.10434 • Published May 11 • 30
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Paper • 2605.10434 • Published May 11 • 30
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL Paper • 2604.28123 • Published May 1 • 47
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling Paper • 2604.28185 • Published Apr 30 • 90
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling Paper • 2604.28185 • Published Apr 30 • 90
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling Paper • 2604.28185 • Published Apr 30 • 90