Official Tempo-6B collection: A query-aware framework solving the mismatch between massive video streams and bounded LLM context windows.
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 22
Vision-CAIR/AttSeg-InternVL3-14B
Updated
Vision-CAIR/AttSeg-InternVL2.5-4B
Updated
Vision-CAIR/Tempo-6B
Video-Text-to-Text • Updated • 92 • 3
Vision-CAIR/Tempo-6B-Stage2
Video-Text-to-Text • Updated • 12
Vision-CAIR/Tempo-6B-Stage1
Video-Text-to-Text • Updated • 20
Vision-CAIR/Tempo-6B-Stage0
Video-Text-to-Text • Updated • 12
Vision-CAIR/BFPO-Mistral-7b-v0.1
Text Generation • 7B • Updated • 24 • 1
Vision-CAIR/LongVU_Llama3_2_1B
Video-Text-to-Text • Updated • 15 • 12
Vision-CAIR/LongVU_Llama3_2_3B_img
Updated • 18 • 6
Vision-CAIR/LongVU_Qwen2_7B_img
Updated • 26 • 5