PhyProbe: Rethinking Physical Consistency Evaluation in Generated Videos Paper • 2609.38377 • Published 15 days ago
VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations Paper • 2610.00994 • Published 13 days ago • 31
VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations Paper • 2610.00994 • Published 13 days ago • 31
World Editing: Intervening on Executable Worlds at Increasing Depth Paper • 2610.02331 • Published 13 days ago • 30
World Editing: Intervening on Executable Worlds at Increasing Depth Paper • 2610.02331 • Published 13 days ago • 30
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation Paper • 2609.38597 • Published 15 days ago • 33
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation Paper • 2609.38597 • Published 15 days ago • 33
Marathoner: Ultra-Long-Horizon Autonomous Intelligence Paper • 2609.34378 • Published 16 days ago • 43
WideSWE: Can Coding Agents Coordinate Changes Across Repositories? Paper • 2609.33382 • Published 17 days ago • 18
WideSWE: Can Coding Agents Coordinate Changes Across Repositories? Paper • 2609.33382 • Published 17 days ago • 18
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published Aug 26 • 333
VGI-Bench: Probing Visual Intelligence in Video Generation Models Paper • 2608.19583 • Published Aug 26 • 333
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding Paper • 2608.16320 • Published Aug 17 • 9
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models Paper • 2607.12463 • Published Jul 14 • 158
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published Jul 9 • 83
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published Jul 9 • 83
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
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors Paper • 2605.10434 • Published May 11 • 30
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction Paper • 2605.05242 • Published May 3 • 126