Vision-CAIR/LongVU_Qwen2_7B
Video-Text-to-Text • 8B • Updated • 199 • 76
LongVU
-
-
Vision-CAIR/LongVU_Llama3_2_3B
Video-Text-to-Text • Updated • 23 • 8 -
Vision-CAIR/LongVU_Llama3_2_3B_img
Updated • 5 • 6 -
Vision-CAIR/LongVU_Qwen2_7B_img
Updated • 8 • 5 -
Vision-CAIR/LongVU_Llama3_2_1B
Video-Text-to-Text • Updated • 22 • 12 -
Vision-CAIR/LongVU_Llama3_2_1B_img
Updated • 2 -
LongVU
🌖88Generate responses to video or image inputs
-
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Paper • 2410.17434 • Published • 27