Small Vision-Language Models are Smart Compressors for Long Video Understanding
Paper • 2604.08120 • Published • 15
Junlin Han
JunlinHan
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
Small Vision-Language Models are Smart Compressors for Long Video Understanding updated a dataset about 1 month ago
JunlinHan/Multi-Level_Existence_Bench updated a dataset about 2 months ago
JunlinHan/Multi-Level_Existence_BenchOrganizations
upvoted a paper 3 days ago