CoPE-VideoLM: Codec Primitives For Efficient Video Language Models
Paper
• 2602.13191 • Published
• 30
Jianhao
Jianhao97
AI & ML interests
None yet
Recent Activity
upvoted a paper 24 days ago
CoPE-VideoLM: Codec Primitives For Efficient Video Language Models liked
a model 8 months ago
Ruicheng/moge-2-vitl-normal authored
a paper
11 months ago
CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic
Data Organizations
upvoted a paper 24 days ago