English

LLaVA-Video: Video Instruction Tuning With Synthetic Data

Computer Vision and Pattern Recognition 2025-08-04 v3 Computation and Language

Abstract

The development of video large multimodal models (LMMs) has been hindered by the difficulty of curating large amounts of high-quality raw data from the web. To address this, we propose an alternative approach by creating a high-quality synthetic dataset specifically for video instruction-following, namely LLaVA-Video-178K. This dataset includes key tasks such as detailed captioning, open-ended question-answering (QA), and multiple-choice QA. By training on this dataset, in combination with existing visual instruction tuning data, we introduce LLaVA-Video, a new video LMM. Our experiments demonstrate that LLaVA-Video achieves strong performance across various video benchmarks, highlighting the effectiveness of our dataset. We plan to release the dataset, its generation pipeline, and the model checkpoints.

Keywords

Cite

@article{arxiv.2410.02713,
  title  = {LLaVA-Video: Video Instruction Tuning With Synthetic Data},
  author = {Yuanhan Zhang and Jinming Wu and Wei Li and Bo Li and Zejun Ma and Ziwei Liu and Chunyuan Li},
  journal= {arXiv preprint arXiv:2410.02713},
  year   = {2025}
}

Comments

Project page: https://llava-vl.github.io/blog/2024-09-30-llava-video/; Accepted at TMLR

R2 v1 2026-06-28T19:07:23.536Z