Jianwei Yang Cvpr 2024 Dates. Working towards developing an accurate mllm system for perception and reasoning, we propose using versatile vision encoders (vcoder) as perception eyes for multimodal. This is the official pytorch implementation of regionclip (cvpr 2022).
My research interests are 3d vision, autonomous driving and unsupervised representation learning. This is the official pytorch implementation of regionclip (cvpr 2022).