Addition: LaVIT, Deepseek-VL and Prismatic VLM

BradyFU / Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

10.88k stars 721 forks source link

Open Hannibal046 opened 3 months ago

Hannibal046 commented 3 months ago

Hi, thanks for the great survey. Here are three missing VLMs:

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models