Video-Oasis: Rethinking Evaluation of Video Understanding Paper • 2603.29616 • Published 9 days ago • 42
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition Paper • 2601.16211 • Published 9 days ago • 40
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views Paper • 2606.29513 • Published 13 days ago • 52
Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking Paper • 2606.15673 • Published Apr 8 • 13
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics Paper • 2605.07755 • Published May 8 • 24
Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation Paper • 2510.19592 • Published Oct 22, 2025 • 13
Streaming Video Question-Answering with In-context Video KV-Cache Retrieval Paper • 2503.00540 • Published Mar 1, 2025 • 3