# SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding

Source: [SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding](<https://www.sota2.com/research/paper/68fa779a1e209131cea74494>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:22:38.768Z

Authors: Mingze Xu, Mingfei Gao, Shiyu Li, Jiasen Lu, Zhe Gan, Zhengfeng Lai, Meng Cao, Kai Kang, Yinfei Yang, Afshin Dehghan

Published: 2025-03-24T17:59:07.000Z

## Abstract

We introduce SlowFast-LLaVA-1.5 (abbreviated as SF-LLaVA-1.5), a family of video large language models (LLMs) offering a token-efficient solution for long-form video understanding. We incorporate the two-stream SlowFast mechanism into a streamlined training pipeline, and perform joint video-image training on a carefully curated data mixture of only publicly available datasets. Our primary focus is on highly efficient model scales (1B and 3B), demonstrating that even relatively small Video LLMs can achieve state-of-the-art performance on video understanding, meeting the demand for mobile-friendly models. Experimental results demonstrate that SF-LLaVA-1.5 achieves superior performance on a wide range of video and image tasks, with robust results at all model sizes (ranging from 1B to 7B). Notably, SF-LLaVA-1.5 achieves state-of-the-art results in long-form video understanding (e.g., LongVideoBench and MLVU) and excels at small scales across various video benchmarks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Long-Video Understanding on LongVideoBench 8s~60m](<https://www.sota2.com/research/sota/long-video-understanding-on-longvideobench-8s-60m.md>): Long Video Understanding; LongVideoBench 8s~60m; Score: 62.5.

- [Long-Video Understanding on LVBench 30m~2h](<https://www.sota2.com/research/sota/long-video-understanding-on-lvbench-30m-2h.md>): Long Video Understanding; LVBench 30m~2h; Score: 45.3.

- [Long-Video Understanding on VideoMME (1-60m, w/o subtitles)](<https://www.sota2.com/research/sota/long-video-understanding-on-videomme-1-60m-w-o-subtitles.md>): Long Video Understanding; VideoMME 1~60m, w/o subtitles; Score: 63.9.

- [Video Understanding on LVBench](<https://www.sota2.com/research/sota/video-understanding-on-lvbench.md>): Video Understanding; LVBench; Overall Accuracy: not recorded.

- [Video Understanding on MLVU (Score, Avg Score, Acc. %)](<https://www.sota2.com/research/sota/video-understanding-on-mlvu-score-avg-score-acc-percent.md>): Video Understanding; MLVU; Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.18943>)

[PDF](<https://arxiv.org/pdf/2503.18943.pdf>)