English

Learning Plug-and-play Memory for Guiding Video Diffusion Models

Computer Vision and Pattern Recognition 2025-12-01 v2 Artificial Intelligence

Abstract

Diffusion Transformer(DiT) based video generation models have recently achieved impressive visual quality and temporal coherence, but they still frequently violate basic physical laws and commonsense dynamics, revealing a lack of explicit world knowledge. In this work, we explore how to equip them with a plug-and-play memory that injects useful world knowledge. Motivated by in-context memory in Transformer-based LLMs, we conduct empirical studies to show that DiT can be steered via interventions on its hidden states, and simple low-pass and high-pass filters in the embedding space naturally disentangle low-level appearance and high-level physical/semantic cues, enabling targeted guidance. Building on these observations, we propose a learnable memory encoder DiT-Mem, composed of stacked 3D CNNs, low-/high-pass filters, and self-attention layers. The encoder maps reference videos into a compact set of memory tokens, which are concatenated as the memory within the DiT self-attention layers. During training, we keep the diffusion backbone frozen, and only optimize the memory encoder. It yields a rather efficient training process on few training parameters (150M) and 10K data samples, and enables plug-and-play usage at inference time. Extensive experiments on state-of-the-art models demonstrate the effectiveness of our method in improving physical rule following and video fidelity. Our code and data are publicly released here: https://thrcle421.github.io/DiT-Mem-Web/.

Keywords

Cite

@article{arxiv.2511.19229,
  title  = {Learning Plug-and-play Memory for Guiding Video Diffusion Models},
  author = {Selena Song and Ziming Xu and Zijun Zhang and Kun Zhou and Jiaxian Guo and Lianhui Qin and Biwei Huang},
  journal= {arXiv preprint arXiv:2511.19229},
  year   = {2025}
}
R2 v1 2026-07-01T07:52:21.909Z