This is the repo for the Video-LLaMA project, which is working on empowering large language models with video and audio understanding capabilities. Video-LLaMA is built on top of BLIP-2 and MiniGPT-4.

This repo contains the code for our ICML 2024 paper LESS: Selecting Influential Data for Targeted Instruction Tuning. In this work, we propose a data selection method to select influential data to ...