[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-tencent-hy-nomas-open-world-model":3,"topics-all":38,"news-related-3a336cad-797b-458c-a175-1cd793aec9bf":57},{"id":4,"title":5,"summary":6,"content":7,"original_url":8,"source_id":9,"tags":10,"translations":24,"news_slug":31,"published_at":32,"created_at":33,"modified_at":34,"is_published":35,"publish_type":36,"image_url":14,"view_count":37},"3a336cad-797b-458c-a175-1cd793aec9bf","腾讯混元开源世界模型Hy-Nomas:单卡4090可跑","腾讯混元公开交互式世界生成模型 Hy-Nomas:8B 扩散骨干,支持多轮自由文本指令与连续相机控制,技术报告已上 arXiv。权重、代码与基准以 Apache 2.0 开源,单张 RTX 4090 可低显存推理,一周内已获 SGLang、ComfyUI、WanGP 集成,作者自述功能与 Genie 4 相同。","世界模型这条赛道本周格外热闹:DeepMind 的 Genie 4 刚掀起新一波讨论,腾讯混元就把自家交互式世界生成模型 Hy-Nomas 的[技术报告](https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.36729)挂上了 arXiv。论文作者在 Hugging Face 评论区写得很直白:Hy-Nomas 支持与 Genie 4 完全相同的功能,但完全开源。敢这么说话,底气是整套工件都放了出来:权重、代码、基准数据集,外加一条轻量适配工作流。\n\n## 它到底能做什么\n\nHy-Nomas 是一个 8B 扩散骨干的视频世界模型:接收多轮自由形式的文本指令或连续相机轨迹,按段生成变长视频,同时用缓存历史保持世界一致性——上一段出现的物体,下一段还在原地。机制上的核心设计,是把结构化视频字幕与动作感知因果注意力对齐:描述性上下文跨段可访问,动作指令则被限制在所属时间窗内,避免旧动作污染新画面。旁边还有一个视觉-语言 Prompt Enhancer,负责把用户请求和多模态交互历史翻译成下一段的结构化条件。训练走多阶段课程:先学因果生成,再逐步引入文本交互、相机控制,之后用模型自生成的历史继续训练,最后做扩散蒸馏。\n\n## 单卡 4090 就能跑\n\n比\"又一个世界模型\"更有信息量的,是部署门槛。Hy-Nomas 采用 Apache 2.0 许可证,官方提供单张 RTX 4090 的低显存推理配置:DiT 权重与 KV 缓存压成 INT8 存储(计算仍走 BF16)、滑动窗口截断历史、CPU offload、FlexAttention 搭配 CUTLASS FP8 解码,再配合蒸馏后 4-8 步去噪。开源一周生态已经跟上:10 月 21 日放出训练推理代码、权重与在线 demo,23 日补 Diffusers 示例,25 日 WanGP 支持,26 日 SGLang、ComfyUI 完成集成,27 日技术报告上 arXiv。Google TPU 侧的社区开发者实测出 720p 实时生成:v6e-4 四芯片上每秒视频只耗约 0.933 秒算力,60 秒连续运行没有迟到帧。\n\n## 需要冷静看待的部分\n\n论文摘要称其在人类评估中优于现有世界模型——这是官方口径,还没有独立评测交叉印证;\"与 Genie 4 功能完全相同\"也是作者自述,两边都该打个引号再看。但就算打折,这套交付的完整度在世界模型赛道仍然少见:模型权重、Hy-Nomas-Bench 基准、LoRA 微调链路、从本地视频制备训练数据的标注工作流,复现研究需要的零件基本都在 GitHub 仓库里。当闭源头部玩家用演示视频秀肌肉时,开源阵营的回答是\"你可以自己跑起来\"。世界模型什么时候从 demo 走进生产?现在任何人都能拿一张 4090 去试答案了。\n","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.36729","97b31c7a-a9f6-4546-83f6-682a3ff34602",[11,15,18,21],{"id":12,"name":13,"slug":13,"description":14,"color":14},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",null,{"id":16,"name":17,"slug":17,"description":14,"color":14},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":19,"name":20,"slug":20,"description":14,"color":14},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",{"id":22,"name":23,"slug":23,"description":14,"color":14},"ebe5dcd1-46b1-4298-b8c2-8e0e2f456e56","video-generation",[25],{"id":26,"lang":27,"title":28,"summary":29,"content":30},"6a7a59cf-4e94-4a2b-9d07-d2aec27cd955","en","Tencent Open-Sources Interactive World Model Hy-Nomas","Tencent open-sources Hy-Nomas, an 8B diffusion world model with multi-turn text and camera control, plus Apache 2.0 weights, code and benchmarks.","World models are having a crowded week: while DeepMind's Genie 4 is still making waves, Tencent's Hunyuan team has posted the technical report for Hy-Nomas, its own interactive world generation model, on arXiv. A paper author put it bluntly in the Hugging Face comments: Hy-Nomas supports exactly the same features as Genie 4, but is fully open-sourced. The confidence comes from a complete artifact drop — weights, code, a benchmark dataset, and a lightweight adaptation workflow.\n\n## What it does\n\nHy-Nomas is a video world model built on an 8B diffusion backbone. It takes multi-turn, free-form text instructions or continuous camera trajectories, generates variable-length video segments, and keeps a cached history so the world stays consistent — objects introduced in one segment are still there in the next. The central design aligns structured video captions with action-aware causal attention: descriptive context stays accessible across segments, while action instructions are restricted to their intended temporal windows, preventing old actions from contaminating new frames. A vision-language Prompt Enhancer translates user requests and multimodal interaction histories into structured conditions for the next segment. Training follows a multi-stage curriculum — causal generation first, then text interaction and camera control, then training on model-generated histories, followed by diffusion distillation.\n\n## It runs on a single RTX 4090\n\nMore telling than \"yet another world model\" is the deployment bar. Hy-Nomas ships under Apache 2.0, with an official low-memory configuration for a single RTX 4090: DiT weights and KV cache stored in INT8 (computation stays in BF16), sliding-window history truncation, CPU offload, and FlexAttention plus CUTLASS FP8 decoding, combined with a distilled 4-8-step denoising loop. The ecosystem moved within a week: training and inference code, weights and an online demo landed October 21, a Diffusers example on October 23, WanGP support on October 25, SGLang and ComfyUI integrations on October 26, and the arXiv report on October 27. On the Google TPU side, a community developer measured real-time 720p generation: about 0.933 seconds of compute per second of video on a v6e-4 slice (4 chips), with no late frames during a 60-second run.\n\n## The caveats\n\nThe abstract claims Hy-Nomas outperforms existing world models in human evaluation — that is the team's own framing, with no independent benchmark to cross-check yet, and \"exactly the same features as Genie 4\" is likewise an author's claim. Even discounted, though, the completeness of the drop is unusual for this track: model weights, the Hy-Nomas-Bench benchmark, a LoRA fine-tuning path, and an annotation workflow for preparing training data from local videos — most of what reproducible research needs is already in the GitHub repository. While closed leaders show off demo reels, the open-source answer is \"you can run it yourself.\" When do world models graduate from demos to production? Now anyone with a 4090 can go find out.\n","tencent-hy-nomas-open-world-model","2026-10-28T17:09:08Z","2026-10-28T17:09:12.482144Z","2026-10-28T17:09:12.482174Z",true,"agent",187,[39,48],{"slug":40,"tag_slug":40,"title_zh":41,"title_en":42,"intro_zh":43,"intro_en":44,"id":45,"is_active":35,"created_at":46,"modified_at":47},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":49,"tag_slug":49,"title_zh":50,"title_en":51,"intro_zh":52,"intro_en":53,"id":54,"is_active":35,"created_at":55,"modified_at":56},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":58},[59,64,69,74,79,84],{"id":60,"title":61,"news_slug":62,"published_at":63},"ab13d62e-1d32-4af6-9d11-ebdb601ff274","Kandinsky 6.0 开源:29B 音视频一体生成","kandinsky-6-0-video-audio-generation-open-source","2026-10-06T19:15:00+00:00",{"id":65,"title":66,"news_slug":67,"published_at":68},"5612d186-46ee-4509-9a93-94045ba004ae","LTX-2.5 开放权重视频模型:4K 反而在 Fast 端点,EXR 色彩管线也焊进去了","ltx-2-5-open-weights-video","2026-08-18T15:20:00+00:00",{"id":70,"title":71,"news_slug":72,"published_at":73},"6f9e9f94-9dcc-4c6c-b254-6c5d0fe8ed37","京东开源 JoyAI-Video-Edit:16B 多模态扩散 Transformer 把视频编辑推进「边播边改」实时流时代","jd-joyai-video-edit-realtime-diffusion","2026-08-10T00:00:00+00:00",{"id":75,"title":76,"news_slug":77,"published_at":78},"bcdc10bc-2f08-4c39-8ffa-e7e34041c112","京东开源 JoyAI-Video-Edit:用 16B 多模态扩散 Transformer 把视频编辑推进「边播边改」实时流时代","jd-joyai-video-edit-real-time-streaming","2026-08-05T03:00:00+00:00",{"id":80,"title":81,"news_slug":82,"published_at":83},"384bb931-49cb-4b1c-b1a8-89495a166699","腾讯ARC Lab:自回归视频的捷径问题,FCP零成本修补","tencent-arc-autoregressive-video-fcp-future-chunk-prediction","2026-10-23T05:05:00+00:00",{"id":85,"title":86,"news_slug":87,"published_at":88},"bef7a773-36fb-406b-949d-8d728b97b242","Matrix-Game 4.0 开源:单卡 60FPS 的实时可玩游戏世界","matrix-game-4-0-open-source-60fps","2026-10-21T13:09:32+00:00"]