Tencent Hy· @TencentHunyuan · X·· 2 小时前精选AI 评分63
AI 导读
腾讯混元发布 Hy-Nomas 交互式视频世界模型的技术报告（arXiv:2610.36729），并开源评测基准 Hy-Nomas-Bench 供可复现研究。该模型支持文本提示词与相机轨迹的自由交互、带世界记忆的长时程生成、面向机器人等领域的轻量 LoRA 适配，并针对消费级 GPU 推理做了优化。官方同时放出与 Genie 4 的对比视频，demo 无需排队即可试用。
推荐理由
技术报告与评测基准 Hy-Nomas-Bench 同步开源，读者可据此复现并对照其与 Genie 4 的差异。
正文 · 原文
Technical report of Hy-Nomas released last Friday: https://arxiv.org/abs/2610.36729
Hy-Nomas-Bench is also open sourced for reproducible research: https://huggingface.co/datasets/tencent/Hy-Nomas-Bench
We also re-create Genie 4 examples with Hy-Nomas. See the full comparison video: Hy-Nomas vs Genie 4 👇
Try our demo right now! No waitlist! https://hy-nomas.hy.tencent.com/
#Hy-Nomas #Genie 4 #WorldModels #VideoGeneration #GenerativeAI
🚀 Introducing Hy-Nomas: An Open Source Free-Form Interactive Video World Model Key Features: * Free-form interaction with text prompts and camera trajectories * Long-horizon generation with world memory * Lightweight LoRA adaptation for specialized domains such as robotics * Optimized for Inference on Consumer GPUs Test it and drop feedback anytime！ 🔗 Website: https://hy-nomas.hy.tencent.com/ 💻 GitHub:https://github.com/Tencent-Hunyuan/Hy-Nomas 🤗 Hugging Face: https://huggingface.co/tencent/Hy-Nomas 🎥 Demo: https://hy-nomas.hy.tencent.com/demo #Hy#WorldModels #VideoGeneration #GenerativeAI在 X 查看被引用的帖子
来源：Tencent Hy · x.com