LLM2CLIP use LLM to teach CLIP vision encoder.

LLM2CLIP

Enabling existing pretrained models to become stronger with minimal fine-tuning

Personne

Portrait de Yifan Yang

Yifan Yang

Research SDE

Portrait de Xufang Luo

Xufang Luo

Senior Researcher

Portrait de Yuqing Yang

Yuqing Yang

Principal Research SDE Manager

Portrait de Qi Dai

Qi Dai

Senior Researcher

Portrait de Xiyang Dai

Xiyang Dai

Principal Researcher

Portrait de Dongdong Chen

Dongdong Chen

Senior Researcher

Portrait de Chong Luo

Chong Luo

Principal Research Manager

Portrait de Lili Qiu

Lili Qiu

Assistant Managing Director