ChuniWorld: Interactive Long-Horizon World Modeling Toward Generative Reality

Alaya Lab

An interactive autoregressive world model with real-time camera control, prompt switching, and long-horizon memory consistency.

---

📰 News

• [2026-06-30] Project page and technical report released.

🚀 Release Roadmap

• Inference code
• Pretrained weights
• Training code
• Training data (partial)

✨ Core Properties

ChuniWorld is built around four core properties — agency, persistence, durability, and responsiveness.

🎮 Agency

Two control channels: a rendered 3D cache with lightweight AdaLN camera modulation for grounded, trajectory-aware navigation, and chunk-level prompt switching to introduce new events mid-generation.

🧠 Persistence

World-consistent memory — an explicit 3D cache reprojected to the queried view for spatial recall, plus a compressed frame-history embedding for temporal continuity, so revisited places stay recognizable.

🛡️ Durability

Long-horizon stability from training on drifted histories and an error bank that re-injects accumulated artifacts into both memory and target, preventing errors from compounding over minute-long rollouts.

⚡ Responsiveness

Real-time interaction via few-step DMD distillation and short temporal chunks, with prompt switching at chunk boundaries to minimize both visual and semantic latency.

👥 Team

• Core Lead: Kaipeng Zhang
• Lead: Chuanhao Li
• Core Contributors: Chuanhao Li, Kaipeng Zhang, Yifan Zhan, Yongtao Ge, Yuanyang Yin
• Contributors: Jiaming Tan, Kang He, Liaoyuan Fan, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, Zhen Li, Zhengyuan Lin, Zhixiang Wang, Zian Meng, Zihui Gao

📬 Contact

For collaboration or business inquiries, contact kaipeng.zhang@shanda.com.

📝 Citation

If you find ChuniWorld useful for your research, please cite:

@article{chuniworld2026,
  title   = {ChuniWorld: Interactive Long-Horizon World Modeling Toward Generative Reality},
  author  = {Alaya Lab},
  journal = {arXiv preprint},
  year    = {2026}
}

📄 License

See LICENSE.