English

LMM will be the next hot spot in the competition

(large multimodal model).

What are the developments:

πŸ€– LLaVa: A competitor to the open-source GPT4-V
πŸ”— Langchain for identifying images: RAG on images
πŸš€ MiniGPT-v2: Visual-language hybrid tasks
🎨 SEED-LLaMA: Simulates human seeing, reading, and imagining

Scroll to Top