MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs
Paper • 2508.18264 • Published • 25 •
4
Sixun Dong
Ironieser
AI & ML interests
None yet
Recent Activity
submitted a paper about 3 hours ago
Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency upvoted a paper about 3 hours ago
Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency upvoted a paper 25 days ago
Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film GenerationOrganizations
commented a
paper 8 months ago
commented a
paper about 1 year ago