LLaVAction: Video Action Recognition LLaVAction: evaluating and training multi-modal large language models for action recognition

✨ Introducing a new #SOTA action recognition large multimodal language model: #LLaVAction!

By @shaokaiye.bsky.social Haozhe Qi, @trackingskills.bsky.social and me!

📝 arxiv.org/abs/2503.18712

🤖 mmathislab.github.io/llavaction/

1/n

Thanks so much!