Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors
Paper
• 2509.00969 • Published
• 3
Wang
Wangxc1000
·
AI & ML interests
None yet
Recent Activity
published
a model 18 days ago
Wangxc1000/Scene-m3 authored
a paper
4 months ago
Seeing More, Saying More: Lightweight Language Experts are Dynamic Video
Token Compressors authored
a paper
4 months ago
ActiveVLN: Towards Active Exploration via Multi-Turn RL in
Vision-and-Language Navigation Organizations
None yet
authored 2 papers 4 months ago