Shaolei Zhang2025-01-08 10:26:28LLaVA-Mini👏is an efficient LMM for image/video understanding using one vision token, offering: (1)⏩lower latency (fast as 40ms per image), (2)🖥️less VRAM usage (support 3-hour video understanding on 2#LLaVA-Mini#高效视觉处理#视频理解