English

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation

Computer Vision and Pattern Recognition 2025-07-09 v3 Machine Learning

Abstract

Diffusion models are successful for synthesizing high-quality videos but are limited to generating short clips (e.g., 2-10 seconds). Synthesizing sustained footage (e.g. over minutes) still remains an open research question. In this paper, we propose MALT Diffusion (using Memory-Augmented Latent Transformers), a new diffusion model specialized for long video generation. MALT Diffusion (or just MALT) handles long videos by subdividing them into short segments and doing segment-level autoregressive generation. To achieve this, we first propose recurrent attention layers that encode multiple segments into a compact memory latent vector; by maintaining this memory vector over time, MALT is able to condition on it and continuously generate new footage based on a long temporal context. We also present several training techniques that enable the model to generate frames over a long horizon with consistent quality and minimal degradation. We validate the effectiveness of MALT through experiments on long video benchmarks. We first perform extensive analysis of MALT in long-contextual understanding capability and stability using popular long video benchmarks. For example, MALT achieves an FVD score of 220.4 on 128-frame video generation on UCF-101, outperforming the previous state-of-the-art of 648.4. Finally, we explore MALT's capabilities in a text-to-video generation setting and show that it can produce long videos compared with recent techniques for long text-to-video generation.

Keywords

Cite

@article{arxiv.2502.12632,
  title  = {MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation},
  author = {Sihyun Yu and Meera Hahn and Dan Kondratyuk and Jinwoo Shin and Agrim Gupta and José Lezama and Irfan Essa and David Ross and Jonathan Huang},
  journal= {arXiv preprint arXiv:2502.12632},
  year   = {2025}
}

Comments

CVPR 2025 Workshop on AI for Content Creation (Oral)

R2 v1 2026-06-28T21:48:24.054Z