Official Tempo-6B collection: A query-aware framework solving the mismatch between massive video streams and bounded LLM context windows.
visioncairgroup
Vision-CAIR
AI & ML interests
None yet
Recent Activity
updated a Space 1 day ago
Vision-CAIR/Tempo upvoted a paper 1 day ago
Small Vision-Language Models are Smart Compressors for Long Video Understanding updated a model 2 days ago
Vision-CAIR/Tempo-6BOrganizations
spaces 6
Running on Zero
Tempo
๐
Smart Compressors for Long Video Understanding
Runtime error
Featured
886
MiniGPT-4
๐
Runtime error
113
MiniGPT-v2
๐
Running on Zero
88
LongVU
๐
Generate responses to video or image inputs
Configuration error
1
MiniGPT-Med
๐
Configuration error
46
MiniGPT4 Video
๐
Answer questions about videos using text
models 17
Vision-CAIR/Tempo-6B
Video-Text-to-Text โข Updated โข 74
Vision-CAIR/BFPO-Mistral-7b-v0.1
Text Generation โข 7B โข Updated โข 10 โข 1
Vision-CAIR/LongVU_Llama3_2_1B
Video-Text-to-Text โข Updated โข 29 โข 12
Vision-CAIR/LongVU_Llama3_2_3B_img
Updated โข 2 โข 6
Vision-CAIR/LongVU_Qwen2_7B_img
Updated โข 6 โข 5
Vision-CAIR/LongVU_Llama3_2_3B
Video-Text-to-Text โข Updated โข 24 โข 8
Vision-CAIR/LongVU_Qwen2_7B
Video-Text-to-Text โข 8B โข Updated โข 176 โข 76
Vision-CAIR/BFPO-redteaming-Zephyr-7b-beta
Text Generation โข 7B โข Updated โข 1
Vision-CAIR/LongVU_Llama3_2_1B_img
Updated
Vision-CAIR/llama_3_2_output
Updated โข 5