CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding
Paper • 2609.39924 • Published • 3
tianyuxuelang
HanXiaotian9656
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 14 days ago
ECHO: Efficient Causal Self-Recursion Beyond Auxiliary Multi-Token Prediction updated a model 6 months ago
HanXiaotian9656/DeepSeek-R1-Distill-Qwen-1.5B-GRPOOrganizations
upvoted 2
papers 14 days ago