腾讯开源 Hy-Nomas 交互式视频世界模型
腾讯混元以 Apache-2.0 许可发布 Hy-Nomas。该模型按视频片段逐段生成世界，支持多轮文本指令、镜头轨迹以及通过 KV 缓存保留上下文；其低内存配置可使用单张 NVIDIA GeForce RTX 4090 运行。腾讯同时发布包含 280 个测试用例的 Hy-Nomas-Bench，覆盖自由交互、镜头导航、文本与镜头联合控制及空间记忆。
Hy-Nomas 将长上下文视频生成、文本与镜头交互控制、开放模型资产和消费级 GPU 部署选项结合起来，并提供了用于评估相关能力的结构化基准。
Computer Science > Computer Vision and Pattern Recognition
arXiv:2610.36729 (cs)
[Submitted on 27 Oct 2026]
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
View a PDF of the paper titled Hy-Nomas: Towards Free-form Interactive World Generation, by Qiaoling Chen and 37 other authors
#Hy-Nomas#Tencent Hunyuan#Hy-Nomas-Bench#Qwen2.5-VL-7B-Instruct#PixelUMM#NVIDIA GeForce RTX 4090