MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
Paper • 2608.17402 • Published • 19
Maxwell Horton
mchorton1991
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding upvoted a paper 3 months ago
R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables updated a dataset 3 months ago
facebook/r3d-benchOrganizations
