README.md

metadata

license: other
license_name: mosaichunk-backbone-licenses
license_link: https://github.com/mosaichunk/MosaiChunk#license
language:
  - en
tags:
  - arxiv:2610.02153
  - video-generation
  - text-to-video
  - image-to-video
  - memory
  - safetensors
datasets:
  - mosaichunk/RememBench

MosaiChunk

Learned memory-router checkpoints for MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation.

Project page · Paper · Code · RememBench

Checkpoint	Backbone
t2v/model.safetensors	RAVEN-adapted MiniMax-H3 (H3-AR)
i2v/model.safetensors	LingBot-World-Infinity

Each folder contains router weights and config.json. The weights are exported without changing tensor values; optimizer and training state are excluded.

These checkpoints require their corresponding frozen video backbone. T2V also requires the pretrained RAVEN streaming adapter. Backbone and adapter weights are not bundled here.

Download

from huggingface_hub import snapshot_download

snapshot_download("mosaichunk/MosaiChunk", local_dir="checkpoints/MosaiChunk")

See the code repository for training and inference.

License

Each router checkpoint is subject to the license of its backbone:

• i2v/: LingBot-World-v2, CC BY-NC-SA 4.0
• t2v/: MiniMax-H3 with the RAVEN streaming adapter, MiniMax-H3 Community License Agreement

The checkpoints do not include backbone or adapter weights and grant no rights to them.

Citation

@misc{zhang2026mosaichunkcompositingspatiotemporalmemory,
      title={MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation},
      author={Yiwen Zhang and Haocheng Xi and Michael Tian-Yue Liu and Alexei A. Efros and Hadar Averbuch-Elor and Qianqian Wang and Haiwen Feng},
      year={2026},
      eprint={2610.02153},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2610.02153},
}