Tencent's Hy-Nomas generates video worlds that respond to text and camera commands| title | Hy-Nomas: Towards Free-form Interactive World Generation |
|---|---|
| authors | Qiaoling Chen, Jiaxiang Cheng, Xueqing Deng, Tiankai Hang, Ji Hou, Jiaqi Li, Yifan Liu, Tao Lu, Junshu Tang, Yu Tang, Yao Teng, Yu Tian, Heng Wang, Weizhi Wang, Xiyao Wang, Xilun Wu, Mingyu Yang, Yangbin Yu, Rui Zhao, Longjun Cao, Linghao Chen, Haoyi Duan, Jiaming Han, Mingji Han, Enhua Jiang, Shunkai Li, Yanzhe Liang, Qinwei Ma, Cong Wang, Lei Wang, Bing Wu, Ke Xing, Ray Ying, Zhentao Yu, Key Zhang, Yuan Zhou, Zhengguang Zhou, Kai Zou |
| date | 2026-10-27 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.36729 |
| affiliation | Tencent Hunyuan |
| upvotes | 122 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| dispatch | Tencent's Hy-Nomas generates video worlds that respond to text and camera commands |
| primer | World models |
| abstract | Interactive world generation requires models to follow successive commands while preserving relevant history and action consequences. We present Hy-Nomas, a video world model with an 8B diffusion backbone that supports free-form text instructions and continuous camera control across multiple interaction turns. It generates variable-length segments conditioned on current inputs and cached history. Our central design aligns structured video captions with action-aware causal attention: descriptive context remains accessible across segments, while action instructions are restricted to their intended temporal windows. A vision-language Prompt Enhancer (PE) translates user requests and multimodal interaction histories into structured conditions for the next segment. A multi-stage curriculum progressively introduces causal generation, text interaction, camera control, and training on model-generated histories, followed by diffusion distillation. In human evaluation, Hy-Nomas shows superior performance over existing world models. We release model weights, code and benchmarks, together with a lightweight adaptation workflow, to support reproducible research on interactive world generation. |
cite
@misc{chen2026hy,
title={Hy-Nomas: Towards Free-form Interactive World Generation},
author={Qiaoling Chen and Jiaxiang Cheng and Xueqing Deng and Tiankai Hang and Ji Hou and Jiaqi Li and Yifan Liu and Tao Lu and Junshu Tang and Yu Tang and Yao Teng and Yu Tian and Heng Wang and Weizhi Wang and Xiyao Wang and Xilun Wu and Mingyu Yang and Yangbin Yu and Rui Zhao and Longjun Cao and Linghao Chen and Haoyi Duan and Jiaming Han and Mingji Han and Enhua Jiang and Shunkai Li and Yanzhe Liang and Qinwei Ma and Cong Wang and Lei Wang and Bing Wu and Ke Xing and Ray Ying and Zhentao Yu and Key Zhang and Yuan Zhou and Zhengguang Zhou and Kai Zou},
year={2026},
eprint={2610.36729},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.36729}
}