NVLM: Open Frontier-Class Multimodal LLMs - NVIDIA ADLR - 0 views
-
Janos Haits on 04 Oct 24"We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g., Llama 3-V 405B and InternVL 2)."
