Collection by 
Dec 27, 2025
-
UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
Paper • 2312.15715 • Published • 20 -
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
Paper • 2505.23747 • Published • 61 -
VideoPrism: A Foundational Visual Encoder for Video Understanding
Paper • 2402.13217 • Published • 41 -
Scaling RL to Long Videos
Paper • 2507.07966 • Published • 158
