# Multimodal LLM

Adopts an innovative slow-fast architecture to balance temporal resolution and spatial details in video understanding, overcoming the sequence length limitations of traditional large language models.

A video multimodal large language model using a slow-fast architecture, balancing temporal resolution and spatial details, supporting 64-frame video understanding

A multimodal language model based on the Llama-3 architecture, natively supporting audio and text input comprehension, focusing on enhancing large language models' understanding of audio.

VideoLLM-online is a multimodal large language model based on Llama-3-8B-Instruct, focusing on online video understanding and video-text generation tasks.