---
language:
- en
tags:
- arxiv:2610.02153
- video-generation
- text-to-video
- image-to-video
- memory
- safetensors
datasets:
- evanbuzzZ/RememBench
---

# MosaiChunk

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

[Project page](https://mosaichunk.github.io/) · [Paper](https://arxiv.org/abs/2610.02153) · [Code](https://github.com/mosaichunk/MosaiChunk) · [RememBench](https://huggingface.co/datasets/evanbuzzZ/RememBench)

| Checkpoint | Backbone |
|---|---|
| [`t2v/model.safetensors`](t2v/model.safetensors) | RAVEN-adapted MiniMax-H3 (H3-AR) |
| [`i2v/model.safetensors`](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

```python
from huggingface_hub import snapshot_download

snapshot_download("evanbuzzZ/MosaiChunk", local_dir="checkpoints/MosaiChunk")
```

See the [code repository](https://github.com/mosaichunk/MosaiChunk) for training and inference.

## License

The release license is pending. Backbone and streaming-adapter weights retain their respective licenses.