EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding Paper • 2605.26104 • Published May 25 • 2
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition Paper • 2601.16211 • Published Jul 2 • 51
MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens Paper • 2603.12513 • Published Mar 12 • 1
MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens Paper • 2603.12513 • Published Mar 12 • 1