UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces
Paper • 2312.15715 • Published • 20
VLM
-
-
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
Paper • 2505.23747 • Published • 69 -
VideoPrism: A Foundational Visual Encoder for Video Understanding
Paper • 2402.13217 • Published • 41 -
Scaling RL to Long Videos
Paper • 2507.07966 • Published • 161 -
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
Paper • 2512.17012 • Published • 49 -
Latent Implicit Visual Reasoning
Paper • 2512.21218 • Published • 70