Vision-CAIR/LongVU_Qwen2_7B
Video-Text-to-Text
•
Updated
•
1.18k
•
55
LongVU
-
-
Vision-CAIR/LongVU_Llama3_2_3B
Video-Text-to-Text • Updated • 454 • 6 -
Vision-CAIR/LongVU_Llama3_2_3B_img
Updated • 99 • 6 -
Vision-CAIR/LongVU_Qwen2_7B_img
Updated • 52 • 4 -
Vision-CAIR/LongVU_Llama3_2_1B
Video-Text-to-Text • Updated • 229 • 6 -
Running on Zero64🌖
LongVU
-
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Paper • 2410.17434 • Published • 24