Vision-CAIR/Tempo-6B
Video-Text-to-Text • Updated • 125 • 1
Tempo
Official Tempo-6B collection: A query-aware framework solving the mismatch between massive video streams and bounded LLM context windows.
-
-
Vision-CAIR/Tempo-6B-Stage2
Video-Text-to-Text • Updated • 34 -
Vision-CAIR/Tempo-6B-Stage1
Video-Text-to-Text • Updated • 18 -
Vision-CAIR/Tempo-6B-Stage0
Video-Text-to-Text • Updated • 25 -
Small Vision-Language Models are Smart Compressors for Long Video Understanding
Paper • 2604.08120 • Published • 20 -
Tempo
🏃3Smart Compressors for Long Video Understanding