4 papers
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
Bonan Zhang, Shiyu Dong, Quan Hung Tran +9
Vision encoders are a critical component of vision-language models, and scaling their capacity effectively improves performance. However, dense scaling increases compute cost and i…
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
Yushan Liu, Peibo Sun, Shoujie Li +7
World Action Models (WAMs) enhance Vision-Language-Action policies by jointly predicting scene evolution and robot actions, but existing methods usually represent the predicted wor…
Perception Encoder: The best visual embeddings are not at the output of the network
Daniel Bolya, Po-Yao Huang, Peize Sun +15
We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoder…
UniPlane: Unified Plane Detection and Reconstruction from Posed Monocular Videos
Yuzhong Huang, Chen Liu, Ji Hou +3
We present UniPlane, a novel method that unifies plane detection and reconstruction from posed monocular videos. Unlike existing methods that detect planes from local observations…