{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-08-07T02:00:35.291Z","headline":"NVIDIA 发布 Alpamayo 2 Super：面向 Robotaxi 与自动驾驶的 34B 开源视觉-语言-动作模型","description":"NVIDIA 发布 Alpamayo 2 Super，一款 34B 参数的视觉-语言-动作（VLA）模型，专为自动驾驶长尾事件设计，权重采用 Linux 基金会 OpenMDW-1.1 许可，代码为 Apache 2.0，发布首日即可商用。","url":"https://www.aioga.com/news/cmsfu19g30eg5rochm0d4q3po/","mainEntityOfPage":"https://www.aioga.com/news/cmsfu19g30eg5rochm0d4q3po/","datePublished":"2026-08-05T08:25:11.000Z","dateModified":"2026-08-05T08:25:11.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://www.marktechpost.com/2026/08/05/nvidia-alpamayo-2-super-open-vla-model-autonomous-driving","https://aihot.virxact.com/items/cmsfu19g30eg5rochm0d4q3po"],"canonicalUrl":"https://www.aioga.com/news/cmsfu19g30eg5rochm0d4q3po/","directAnswer":{"@type":"Answer","text":"NVIDIA 发布34B参数的 Alpamayo 2 Super 视觉-语言-动作模型，面向自动驾驶长尾事件，权重采用 OpenMDW-1.1 许可，代码采用 Apache 2.0，并支持首日商业使用。","url":"https://www.aioga.com/news/cmsfu19g30eg5rochm0d4q3po/","dateCreated":"2026-08-05T08:25:11.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"marktechpost.com source article","url":"https://www.marktechpost.com/2026/08/05/nvidia-alpamayo-2-super-open-vla-model-autonomous-driving","datePublished":"2026-08-05T08:25:11.000Z","provider":{"@type":"Organization","name":"marktechpost.com","url":"https://www.marktechpost.com/2026/08/05/nvidia-alpamayo-2-super-open-vla-model-autonomous-driving"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmsfu19g30eg5rochm0d4q3po","datePublished":"2026-08-05T08:25:11.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmsfu19g30eg5rochm0d4q3po"}}],"aggregationSource":"MarkTechPost（RSS）","originalPublisher":{"name":"marktechpost.com","url":"https://www.marktechpost.com/2026/08/05/nvidia-alpamayo-2-super-open-vla-model-autonomous-driving"},"geoDeepAnswer":null,"article":{"id":"cmsfu19g30eg5rochm0d4q3po","slug":"cmsfu19g30eg5rochm0d4q3po","url":"https://www.aioga.com/news/cmsfu19g30eg5rochm0d4q3po/","title":"NVIDIA 发布 Alpamayo 2 Super：面向 Robotaxi 与自动驾驶的 34B 开源视觉-语言-动作模型","title_en":"NVIDIA Releases Alpamayo 2 Super： A 34B Open Vision-Language-Action Model for Robotaxis and Autonomous Driving Under OpenMDW-1.1","summary":"NVIDIA 发布 Alpamayo 2 Super，一款 34B 参数的视觉-语言-动作（VLA）模型，专为自动驾驶长尾事件设计，权重采用 Linux 基金会 OpenMDW-1.1 许可，代码为 Apache 2.0，发布首日即可商用。","source":"MarkTechPost（RSS）","sourceUrl":"https://www.marktechpost.com/2026/08/05/nvidia-alpamayo-2-super-open-vla-model-autonomous-driving","aiHotUrl":"https://aihot.virxact.com/items/cmsfu19g30eg5rochm0d4q3po","publishedAt":"2026-08-05T08:25:11.000Z","category":"模型更新","score":79,"selected":true,"articleBody":["NVIDIA has released Alpamayo 2 Super：https://huggingface.co/nvidia/Alpamayo2-Super , a 34B-parameter vision-language-action (VLA) mode：https://blogs.nvidia.com/blog/alpamayo-2-super-open-model-now-available/l for autonomous driving, under an open commercial license. The stated design target is the long-tail events: rare, multi-agent situations that conventional detection-and-prediction stacks handle poorly. The model pairs a 32B VLM backbone, built on NVIDIA Cosmos 3 Super Reasoner and post-trained with reinforcement learning, with a 2.3B diffusion-based action decoder. From one pass over full-surround camera video it emits a planned trajectory, a causal explanation of that trajectory, and a meta-action.","Yes, and for commercial use from day one. The weights are released under OpenMDW-1.1, the Linux Foundation’s permissive license for open model distributions; source code is Apache 2.0. The license covers fine-tuning, derivative models and commercial redistribution. NVIDIA is applying OpenMDW across the entire Alpamayo family, so earlier releases introduced for R&D are now deployable commercially without additional permission.","Inputs are multi-camera RGB video, text, and egomotion history with timestamps. The validated public notebook profiles use six cameras and four historical frames per camera. Egomotion is 3D translation plus a 3×3 rotation matrix, multi-timestep.","The trajectory API returns 64 waypoints spanning 0.1 to 6.4 seconds at 0.1-second intervals. Each waypoint carries ego-frame XYZ and a 3×3 rotation matrix.","Training data is roughly 115,000 hours of multi-camera driving video with egomotion and trajectory annotations. It includes about 3,700,000 Chain-of-Causation (CoC) traces — structured, causally linked explanations of driving decisions. Image training data exceeds one billion images.","On LingoQA：https://github.com/wayveai/LingoQA, Alpamayo 2 Super records a Lingo-Judge score of 79.2 and ranks first among nearly 40 models evaluated. In NVIDIA’s testing it beat Qwen2.5-VL 72B by 17.0 points, Gemini 2.5 Pro by 15.1, and GPT-4o by 23.2.","Two more numbers matter for planning work. Closed-loop evaluation with AlpaSim：https://github.com/NVlabs/alpasim on 910 scenarios from the PhysicalAI-AV-NuRec：https://huggingface.co/datasets/nvidia/PhysicalAI-Autonomous-Vehicles-NuRec dataset gives an AlpaSim score of 1.50 ± 0.13. Open-loop evaluation on 937 challenging samples from the PhysicalAI-AV：https://huggingface.co/datasets/nvidia/PhysicalAI-Autonomous-Vehicles dataset gives minADE₆ at 6.4s of 0.911m.","For each driving situation, the model produces a trajectory, a CoC trace explaining the decision, a meta-action such as yield or lane change, reasoning auto-labels, and visual question answering with 2D grounding.","That combination is what makes the release interesting operationally. Developers can tie what the model observed to the action it chose. CoC traces integrate with NVIDIA Halos：https://www.nvidia.com/en-us/ai-trust-center/halos/autonomous-vehicles/ safety-validation workflows and support AI safety aligned with ISO/PAS 8800.","Used as an autolabeler on proprietary fleet data, NVIDIA says the model compresses annotation cycles from months to days.","Need to partner with us for promoting your GitHub Repo OR Hugging Face Page OR Product Release OR Webinar etc.? Connect with us ：https://forms.gle/wbash1wF6efRj8G58","Asif Razzaq is the CEO of Marktechpost Media Inc.. As a visionary entrepreneur and engineer, Asif is committed to harnessing the potential of Artificial Intelligence for social good. His most recent endeavor is the launch of an Artificial Intelligence Media Platform, Marktechpost, which stands out for its in-depth coverage of machine learning and deep learning news that is both technically sound and easily understandable by a wide audience. The platform boasts of over 2 million monthly views, illustrating its popularity among audiences.","[FREE GUIDE] Securing AI Agents, MCP Servers & LLM Apps ：https://pxllnk.co/lxn88m"],"articleImages":[{"sourceUrl":"https://www.marktechpost.com/wp-content/uploads/2019/06/Screen-Shot-2021-09-14-at-9.02.24-AM-300x300.png","alt":"","afterParagraph":10,"url":"/media/articles/cmsfu19g30eg5rochm0d4q3po/787a6d54564e8e19.webp"},{"sourceUrl":"https://www.marktechpost.com/wp-content/uploads/2026/08/blog6176-1-1-100x70.png","alt":"Pixel-Native RAG: A Practical Guide to Visual Document Indexing","afterParagraph":11,"url":"/media/articles/cmsfu19g30eg5rochm0d4q3po/5c8b01b8b70a10f0.png"},{"sourceUrl":"https://www.marktechpost.com/wp-content/uploads/2026/08/high-level-description-a-monochrome-cybe_2rr6n78EUGGOOwTBaf3UzA_gSBnpjrRS5CwRLN0TlRb5g_cover_2k-100x70.png","alt":"Building an Advanced AI Skill Security Auditing Pipeline with NVIDIA SkillSpector, LangGraph, YARA Rules, SARIF, and CI Policy Gates","afterParagraph":11,"url":"/media/articles/cmsfu19g30eg5rochm0d4q3po/542fa098b88910cd.png"}],"mediaStatus":"ok","articleBodyZh":["NVIDIA 发布了 Alpamayo 2 Super：https：//huggingface.co/nvidia/Alpamayo2-Super，一款 34B 参数的视觉语言动作（VLA）模式：https：//blogs.nvidia.com/blog/alpamayo-2-super-open-model-now-available/l，采用开放商业许可，适用于自动驾驶。设计目标是长尾事件：传统检测与预测堆栈处理不佳的罕见多代理情形。该模型将基于NVIDIA Cosmos 3 Super Reasoner构建、经过强化学习后期训练的32B VLM骨干，与基于扩散的2.3B动作解码器配对。从一次全环绕摄像机视频的扫描中，它发出一个有计划的轨迹、对该轨迹的因果解释以及一个元动作。","是的，而且从第一天起就是商业用途。权重根据 OpenMDW-1.1 发布，这是 Linux 基金会对开放模型发行版的宽松许可;源代码为Apache 2.0。该许可证涵盖微调、衍生模型和商业再分发。NVIDIA 正在将 OpenMDW 应用于整个 Alpamayo 系列，因此早期为研发推出的版本现在可以在无需额外许可的情况下商业部署。","输入是多机位RGB视频、文本和带有时间戳的自我动态历史。经过验证的公共笔记本配置文件使用六个摄像头和四个历史帧。自我运动是三维平移加上一个3×3旋转矩阵，多时间步。","轨迹API返回64个航点，间隔0.1至6.4秒，间隔0.1秒。每个航点携带自我框架XYZ和一个3×3旋转矩阵。","训练数据大约是115,000小时的多机位驾驶视频，包含自我运动和轨迹标注。它包含约3,700,000条因果链（CoC）痕迹——结构化、因果关联的驱动决策解释。图像训练数据超过十亿张。","在LingoQA：https：//github.com/wayveai/LingoQA，Alpamayo 2 Super 在 Lingo-Judge 中得分为79.2，在近40个评估模型中排名第一。在NVIDIA的测试中，它领先Qwen2.5-VL 72B17.0个百分点，Gemini 2.5 Pro领先15.1个百分点，GPT-4o领先23.2个百分点。","规划工作还需要关注另外两个数字。在 PhysicalAI-AV-NuRec：https://huggingface.co/datasets/nvidia/PhysicalAI-Autonomous-Vehicles-NuRec 数据集的 910 个场景上，使用 AlpaSim：https://github.com/NVlabs/alpasim 进行闭环评估时，AlpaSim 得分为 1.50 ± 0.13。在 PhysicalAI-AV：https://huggingface.co/datasets/nvidia/PhysicalAI-Autonomous-Vehicles 数据集的 937 个具有挑战性的样本上进行开环评估时，6.4 秒时的 minADE₆ 为 0.911 米。","对于每个驾驶场景，模型会产生一条轨迹、一条说明决策的 CoC 轨迹、一项元动作（如让行或变道）、推理自动标签，以及带有二维定位的视觉问答。","这种组合使得该版本在操作上非常有趣。开发者可以将模型所观察的内容与其选择的动作联系起来。CoC 轨迹可以与 NVIDIA Halos：https://www.nvidia.com/en-us/ai-trust-center/halos/autonomous-vehicles/ 的安全验证工作流程集成，并支持符合 ISO/PAS 8800 标准的 AI 安全。","NVIDIA 表示，当模型作为专有车队数据的自动标注工具使用时，可将标注周期从数月缩短至数天。","需要与我们合作以推广您的 GitHub 仓库或 Hugging Face 页面或产品发布或网络研讨会等吗？请联系我们： https://forms.gle/wbash1wF6efRj8G58","Asif Razzaq 是 Marktechpost Media Inc. 的首席执行官。作为一位有远见的企业家和工程师，Asif 致力于利用人工智能的潜力造福社会。他最近的项目是推出人工智能媒体平台 Marktechpost，该平台以对机器学习和深度学习新闻的深入报道而著称，技术上严谨且易于广泛受众理解。该平台每月浏览量超过 200 万次，显示了其在受众中的受欢迎程度。","[免费指南] 保护 AI 代理、MCP 服务器和大语言模型应用程序：https://pxllnk.co/lxn88m"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"NVIDIA 发布34B参数的 Alpamayo 2 Super 视觉-语言-动作模型，面向自动驾驶长尾事件，权重采用 OpenMDW-1.1 许可，代码采用 Apache 2.0，并支持首日商业使用。","background":"该模型由32B视觉语言模型骨干与2.3B扩散式动作解码器组成，可处理多摄像头视频、文本和自车运动历史，并输出轨迹、因果解释及元动作。","viewpoint":"Aioga 判断，开放许可与轨迹、解释联合输出，可能降低研究者和企业评估自动驾驶长尾场景的门槛；但材料未说明其已通过真实道路监管或量产验证。","implications":"值得关注的是，NVIDIA披露模型在 LingoQA、AlpaSim 和开放环评测中取得具体成绩，但这些结果来自指定基准与测试样本，不能直接等同于实际道路安全表现。","nextStep":"后续应核验模型在不同传感器配置、真实道路和极端长尾场景中的表现，并关注 OpenMDW-1.1 商业条款、数据合规及安全责任如何落地。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-08-05T11:31:48.328Z","sourceHash":"e6c2ae6b7d0b0812","review":{"approved":true,"groundedness":96,"clarity":93,"duplicationRisk":18,"blockingIssues":[],"notes":["“可能降低……门槛”已明确标注为 Aioga 的判断，没有冒充来源事实。","对基准成绩不能直接等同于实际道路安全表现的限定合理，避免了从指定评测结果过度外推。","候选内容未复述具体评测分数；如需增强信息密度，可补充 Lingo-Judge 79.2、AlpaSim 1.50±0.13 和 minADE₆ 0.911m，但这属于可选完善。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","low-source-overlap","no-html","independent-ai-review"]}},"tags":["模型更新","MarkTechPost（RSS）"],"translations":{"zh-CN":{"title":"NVIDIA 发布 Alpamayo 2 Super：面向 Robotaxi 与自动驾驶的 34B 开源视觉-语言-动作模型","summary":"NVIDIA 发布 Alpamayo 2 Super，一款 34B 参数的视觉-语言-动作（VLA）模型，专为自动驾驶长尾事件设计，权重采用 Linux 基金会 OpenMDW-1.1 许可，代码为 Apache 2.0，发布首日即可商用。","category":"模型更新","source":"marktechpost.com","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA 发布 Alpamayo 2 Super：面向 Robotaxi 与自动驾驶的 34B 开源视觉-语言-动作模型 - Aioga AI资讯","description":"NVIDIA 发布 Alpamayo 2 Super，一款 34B 参数的视觉-语言-动作（VLA）模型，专为自动驾驶长尾事件设计，权重采用 Linux 基金会 OpenMDW-1.1 许可，代码为 Apache 2.0，发布首日即可商用。","url":"https://www.aioga.com/news/cmsfu19g30eg5rochm0d4q3po/"},"en":{"title":"NVIDIA Releases Alpamayo 2 Super: A 34B Open-Source Vision-Language-Action Model for Robotaxi and Autonomous Driving","summary":"NVIDIA released Alpamayo 2 Super, a 34B-parameter vision-language-action (VLA) model designed for autonomous driving long-tail events. The weights are licensed under the Linux Foundation's OpenMDW-1.1, the code is under Apache 2.0, and it can be used commercially on the first day of release.","category":"Models","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA Releases Alpamayo 2 Super: A 34B Open-Source Vision-Language-Action Model for Robotaxi and Autonomous Driving - Aioga AI News","description":"NVIDIA released Alpamayo 2 Super, a 34B-parameter vision-language-action (VLA) model designed for autonomous driving long-tail events. The weights are licensed under the Linux Foun...","url":"https://www.aioga.com/en/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:03:56.177Z"},"ja":{"title":"NVIDIA、Alpamayo 2 Super を発表：Robotaxi と自動運転向けの 34B オープンソース視覚・言語・動作モデル","summary":"NVIDIAは34Bパラメータのビジュアル・言語・アクション（VLA）モデルであるAlpamayo 2 Superを発表しました。これは自動運転の長尾イベント向けに設計されており、重みはLinux基金会のOpenMDW-1.1ライセンス、コードはApache 2.0で、リリース初日から商用利用が可能です。","category":"モデル更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA、Alpamayo 2 Super を発表：Robotaxi と自動運転向けの 34B オープンソース視覚・言語・動作モデル - Aioga AIニュース","description":"NVIDIAは34Bパラメータのビジュアル・言語・アクション（VLA）モデルであるAlpamayo 2 Superを発表しました。これは自動運転の長尾イベント向けに設計されており、重みはLinux基金会のOpenMDW-1.1ライセンス、コードはApache 2.0で、リリース初日から商用利用が可能です。","url":"https://www.aioga.com/ja/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:04:06.361Z"},"ko":{"title":"NVIDIA, Robotaxi 및 자율주행을 위한 34B 오픈소스 비주얼-언어-액션 모델 Alpamayo 2 Super 발표","summary":"NVIDIA는 Alpamayo 2 Super를 발표했으며, 이는 34B 매개변수를 가진 시각-언어-행동(VLA) 모델로, 자율주행 장기 꼬리 이벤트를 위해 설계되었고, 가중치는 Linux 재단 OpenMDW-1.1 라이선스를 사용하며, 코드는 Apache 2.0이며, 출시 첫날부터 상업적으로 사용할 수 있습니다.","category":"모델 업데이트","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA, Robotaxi 및 자율주행을 위한 34B 오픈소스 비주얼-언어-액션 모델 Alpamayo 2 Super 발표 - Aioga AI 뉴스","description":"NVIDIA는 Alpamayo 2 Super를 발표했으며, 이는 34B 매개변수를 가진 시각-언어-행동(VLA) 모델로, 자율주행 장기 꼬리 이벤트를 위해 설계되었고, 가중치는 Linux 재단 OpenMDW-1.1 라이선스를 사용하며, 코드는 Apache 2.0이며, 출시 첫날부터 상업적으로 사용할 수 있습니다.","url":"https://www.aioga.com/ko/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:05:03.552Z"},"es":{"title":"NVIDIA lanza Alpamayo 2 Super: modelo abierto de 34B de visión-lenguaje-acción dirigido a Robotaxi y conducción autónoma","summary":"NVIDIA lanzó Alpamayo 2 Super, un modelo visual-lenguaje-acción (VLA) de 34 mil millones de parámetros, diseñado para eventos de cola larga en conducción autónoma; los pesos están bajo la licencia OpenMDW-1.1 de la Fundación Linux y el código bajo Apache 2.0, disponible para uso comercial desde el primer día de su lanzamiento.","category":"Modelos","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA lanza Alpamayo 2 Super: modelo abierto de 34B de visión-lenguaje-acción dirigido a Robotaxi y conducción autónoma - Aioga Noticias de IA","description":"NVIDIA lanzó Alpamayo 2 Super, un modelo visual-lenguaje-acción (VLA) de 34 mil millones de parámetros, diseñado para eventos de cola larga en conducción autónoma; los pesos están...","url":"https://www.aioga.com/es/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:04:58.936Z"},"fr":{"title":"NVIDIA lance Alpamayo 2 Super : un modèle ouvert vision-langage-action 34B destiné aux Robotaxi et à la conduite autonome","summary":"NVIDIA a publié Alpamayo 2 Super, un modèle visuel-langage-action (VLA) de 34 milliards de paramètres, conçu pour les événements rares en conduite autonome, avec des poids sous licence OpenMDW-1.1 de la Linux Foundation et un code sous Apache 2.0, utilisable commercialement dès le premier jour de sa sortie.","category":"Modèles","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA lance Alpamayo 2 Super : un modèle ouvert vision-langage-action 34B destiné aux Robotaxi et à la conduite autonome - Aioga Actualités IA","description":"NVIDIA a publié Alpamayo 2 Super, un modèle visuel-langage-action (VLA) de 34 milliards de paramètres, conçu pour les événements rares en conduite autonome, avec des poids sous lic...","url":"https://www.aioga.com/fr/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:05:53.094Z"},"de":{"title":"NVIDIA veröffentlicht Alpamayo 2 Super: Ein 34B Open-Source-Visuell-Sprach-Aktionsmodell für Robotaxis und autonomes Fahren","summary":"NVIDIA hat Alpamayo 2 Super veröffentlicht, ein 34B-Parameter-Visuell-Sprach-Aktions-(VLA)-Modell, das speziell für Long-Tail-Ereignisse beim autonomen Fahren entwickelt wurde. Die Gewichte sind unter der OpenMDW-1.1-Lizenz der Linux Foundation lizenziert, der Code unter Apache 2.0, und es kann bereits am ersten Veröffentlichungstag kommerziell genutzt werden.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA veröffentlicht Alpamayo 2 Super: Ein 34B Open-Source-Visuell-Sprach-Aktionsmodell für Robotaxis und autonomes Fahren - Aioga KI-News","description":"NVIDIA hat Alpamayo 2 Super veröffentlicht, ein 34B-Parameter-Visuell-Sprach-Aktions-(VLA)-Modell, das speziell für Long-Tail-Ereignisse beim autonomen Fahren entwickelt wurde. Die...","url":"https://www.aioga.com/de/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:05:48.142Z"},"pt-BR":{"title":"NVIDIA lança Alpamayo 2 Super: modelo de visão-linguagem-ação open source de 34B voltado para Robotaxi e direção autônoma","summary":"A NVIDIA lançou o Alpamayo 2 Super, um modelo visual-linguagem-ação (VLA) com 34 bilhões de parâmetros, projetado para eventos raros em direção autônoma. Os pesos utilizam a licença OpenMDW-1.1 da Linux Foundation, o código é Apache 2.0, e pode ser usado comercialmente no primeiro dia de lançamento.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA lança Alpamayo 2 Super: modelo de visão-linguagem-ação open source de 34B voltado para Robotaxi e direção autônoma - Aioga Notícias de IA","description":"A NVIDIA lançou o Alpamayo 2 Super, um modelo visual-linguagem-ação (VLA) com 34 bilhões de parâmetros, projetado para eventos raros em direção autônoma. Os pesos utilizam a licenç...","url":"https://www.aioga.com/pt-BR/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:06:51.106Z"},"ru":{"title":"NVIDIA выпустила Alpamayo 2 Super: 34-миллиардная открытая модель визуально-языково-действий для Robotaxi и автономного вождения","summary":"NVIDIA выпустила Alpamayo 2 Super, модель визуально-языковых-действий (VLA) с 34 миллиардами параметров, разработанную для редких событий в автономном вождении. Вес модели лицензирован по лицензии OpenMDW-1.1 Фонда Linux, код — по Apache 2.0, и она может использоваться в коммерческих целях с первого дня публикации.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA выпустила Alpamayo 2 Super: 34-миллиардная открытая модель визуально-языково-действий для Robotaxi и автономного вождения - Aioga Новости ИИ","description":"NVIDIA выпустила Alpamayo 2 Super, модель визуально-языковых-действий (VLA) с 34 миллиардами параметров, разработанную для редких событий в автономном вождении. Вес модели лицензир...","url":"https://www.aioga.com/ru/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:06:47.255Z"},"ar":{"title":"أصدرت NVIDIA نموذج Alpamayo 2 Super: نموذج مفتوح المصدر برقم 34B للرؤية-لغة-حركة مخصص لروبوتاكسي والقيادة الذاتية","summary":"أصدرت NVIDIA نموذج Alpamayo 2 Super، وهو نموذج بصري-لغوي-حركي (VLA) يحتوي على 34 مليار معلمة، مصمم خصيصًا لحوادث الذيل الطويل في القيادة الذاتية، والوزن مرخّص بموجب ترخيص OpenMDW-1.1 من مؤسسة Linux، والكود بموجب Apache 2.0، ويمكن استخدامه تجاريًا في يوم الإصدار الأول.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"أصدرت NVIDIA نموذج Alpamayo 2 Super: نموذج مفتوح المصدر برقم 34B للرؤية-لغة-حركة مخصص لروبوتاكسي والقيادة الذاتية - Aioga أخبار الذكاء الاصطناعي","description":"أصدرت NVIDIA نموذج Alpamayo 2 Super، وهو نموذج بصري-لغوي-حركي (VLA) يحتوي على 34 مليار معلمة، مصمم خصيصًا لحوادث الذيل الطويل في القيادة الذاتية، والوزن مرخّص بموجب ترخيص OpenMDW-1...","url":"https://www.aioga.com/ar/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:07:47.095Z"},"hi":{"title":"NVIDIA ने Alpamayo 2 Super जारी किया: Robotaxi और स्वचालित ड्राइविंग के लिए 34B ओपन-सोर्स विज़ुअल-लैंग्वेज-एक्शन मॉडल","summary":"NVIDIA ने Alpamayo 2 Super लॉन्च किया, एक 34B पैरामीटर वाला विज़ुअल-भाषा-एक्शन (VLA) मॉडल, विशेष रूप से ऑटोमोटिव लंबे-पूंछ वाले घटनाओं के लिए डिज़ाइन किया गया, वज़न Linux फाउंडेशन OpenMDW-1.1 लाइसेंस के तहत उपलब्ध हैं, कोड Apache 2.0 के तहत है, और इसे रिलीज़ के पहले ही दिन व्यावसायिक उपयोग के लिए उपलब्ध किया जा सकता है।","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA ने Alpamayo 2 Super जारी किया: Robotaxi और स्वचालित ड्राइविंग के लिए 34B ओपन-सोर्स विज़ुअल-लैंग्वेज-एक्शन मॉडल - Aioga AI समाचार","description":"NVIDIA ने Alpamayo 2 Super लॉन्च किया, एक 34B पैरामीटर वाला विज़ुअल-भाषा-एक्शन (VLA) मॉडल, विशेष रूप से ऑटोमोटिव लंबे-पूंछ वाले घटनाओं के लिए डिज़ाइन किया गया, वज़न Linux फाउंडेशन...","url":"https://www.aioga.com/hi/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:07:50.882Z"},"it":{"title":"NVIDIA lancia Alpamayo 2 Super: modello visivo-linguaggio-azione open source da 34B per Robotaxi e guida autonoma","summary":"NVIDIA ha rilasciato Alpamayo 2 Super, un modello visivo-linguaggio-azione (VLA) con 34 miliardi di parametri, progettato per eventi tail lunghi nella guida autonoma, i pesi sono sotto licenza OpenMDW-1.1 della Linux Foundation, il codice è Apache 2.0 e può essere utilizzato commercialmente dal primo giorno del rilascio.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA lancia Alpamayo 2 Super: modello visivo-linguaggio-azione open source da 34B per Robotaxi e guida autonoma - Aioga Notizie IA","description":"NVIDIA ha rilasciato Alpamayo 2 Super, un modello visivo-linguaggio-azione (VLA) con 34 miliardi di parametri, progettato per eventi tail lunghi nella guida autonoma, i pesi sono s...","url":"https://www.aioga.com/it/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:08:41.271Z"},"nl":{"title":"NVIDIA lanceert Alpamayo 2 Super: 34B open source visueel-taal-actie model voor Robotaxi en zelfrijdende auto's","summary":"NVIDIA heeft Alpamayo 2 Super uitgebracht, een 34B parameters visueel-taal-actie (VLA) model, speciaal ontworpen voor lange staart gebeurtenissen in autonoom rijden. De gewichten gebruiken de Linux Foundation OpenMDW-1.1 licentie en de code is Apache 2.0, en het kan commerciële toepassingen direct op de eerste dag na de release worden gebruikt.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA lanceert Alpamayo 2 Super: 34B open source visueel-taal-actie model voor Robotaxi en zelfrijdende auto's - Aioga AI-nieuws","description":"NVIDIA heeft Alpamayo 2 Super uitgebracht, een 34B parameters visueel-taal-actie (VLA) model, speciaal ontworpen voor lange staart gebeurtenissen in autonoom rijden. De gewichten g...","url":"https://www.aioga.com/nl/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:08:45.182Z"},"tr":{"title":"NVIDIA, Robotaksi ve otonom sürüş için 34B açık kaynak görsel-dil-aksiyon modeli Alpamayo 2 Super'i yayınladı","summary":"NVIDIA, otomatik sürüş uzun kuyruk olayları için tasarlanmış 34B parametreli bir görsel-dil-hareket (VLA) modeli olan Alpamayo 2 Super’i yayımladı; ağırlıklar Linux Vakfı OpenMDW-1.1 lisansı altında, kod ise Apache 2.0 ile sunuluyor ve yayımlandığı ilk gün ticari kullanıma uygun.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA, Robotaksi ve otonom sürüş için 34B açık kaynak görsel-dil-aksiyon modeli Alpamayo 2 Super'i yayınladı - Aioga AI Haberleri","description":"NVIDIA, otomatik sürüş uzun kuyruk olayları için tasarlanmış 34B parametreli bir görsel-dil-hareket (VLA) modeli olan Alpamayo 2 Super’i yayımladı; ağırlıklar Linux Vakfı OpenMDW-1...","url":"https://www.aioga.com/tr/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:09:40.705Z"},"vi":{"title":"NVIDIA phát hành Alpamayo 2 Super: Mô hình thị giác-ngôn ngữ-hành động mã nguồn mở 34B hướng tới Robotaxi và lái xe tự động","summary":"NVIDIA phát hành Alpamayo 2 Super, một mô hình thị giác-ngôn ngữ-hành động (VLA) 34 tỷ tham số, được thiết kế cho các sự kiện dài đuôi trong lái xe tự động, trọng số được cấp phép theo OpenMDW-1.1 của Linux Foundation, mã nguồn theo Apache 2.0, có thể thương mại hóa ngay trong ngày ra mắt.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA phát hành Alpamayo 2 Super: Mô hình thị giác-ngôn ngữ-hành động mã nguồn mở 34B hướng tới Robotaxi và lái xe tự động - Tin tức AI Aioga","description":"NVIDIA phát hành Alpamayo 2 Super, một mô hình thị giác-ngôn ngữ-hành động (VLA) 34 tỷ tham số, được thiết kế cho các sự kiện dài đuôi trong lái xe tự động, trọng số được cấp phép...","url":"https://www.aioga.com/vi/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:09:38.026Z"},"id":{"title":"NVIDIA merilis Alpamayo 2 Super: model visi-bahasa-aksi open source 34B untuk Robotaxi dan mengemudi otomatis","summary":"NVIDIA merilis Alpamayo 2 Super, sebuah model Visual-Bahasa-Aksi (VLA) dengan 34 miliar parameter, dirancang khusus untuk kejadian ekor panjang dalam mengemudi otomatis, bobot menggunakan lisensi OpenMDW-1.1 dari Linux Foundation, kode menggunakan Apache 2.0, dan dapat digunakan secara komersial pada hari pertama dirilis.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA merilis Alpamayo 2 Super: model visi-bahasa-aksi open source 34B untuk Robotaxi dan mengemudi otomatis - Berita AI Aioga","description":"NVIDIA merilis Alpamayo 2 Super, sebuah model Visual-Bahasa-Aksi (VLA) dengan 34 miliar parameter, dirancang khusus untuk kejadian ekor panjang dalam mengemudi otomatis, bobot meng...","url":"https://www.aioga.com/id/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:10:44.697Z"},"th":{"title":"NVIDIA เปิดตัว Alpamayo 2 Super: โมเดลเปิดโค้ดวิชวล-ภาษา-การกระทำขนาด 34B สำหรับ Robotaxi และการขับขี่อัตโนมัติ","summary":"NVIDIA เปิดตัว Alpamayo 2 Super โมเดลการมองเห็น-ภาษา-การเคลื่อนไหว (VLA) ขนาด 34B พารามิเตอร์ ออกแบบมาสำหรับเหตุการณ์หางยาวในการขับขี่อัตโนมัติ น้ำหนักใช้ใบอนุญาต OpenMDW-1.1 ของ Linux Foundation โค้ดเป็น Apache 2.0 สามารถใช้เชิงพาณิชย์ได้ตั้งแต่วันแรกที่เปิดตัว","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA เปิดตัว Alpamayo 2 Super: โมเดลเปิดโค้ดวิชวล-ภาษา-การกระทำขนาด 34B สำหรับ Robotaxi และการขับขี่อัตโนมัติ - ข่าว AI Aioga","description":"NVIDIA เปิดตัว Alpamayo 2 Super โมเดลการมองเห็น-ภาษา-การเคลื่อนไหว (VLA) ขนาด 34B พารามิเตอร์ ออกแบบมาสำหรับเหตุการณ์หางยาวในการขับขี่อัตโนมัติ น้ำหนักใช้ใบอนุญาต OpenMDW-1.1 ของ L...","url":"https://www.aioga.com/th/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:10:46.071Z"},"pl":{"title":"NVIDIA wprowadza Alpamayo 2 Super: 34-miliardowy otwarty model wizualno-językowo-ruchowy dla Robotaxi i autonomicznej jazdy","summary":"NVIDIA ogłosiła Alpamayo 2 Super, model wizualno-językowo-ruchowy (VLA) o 34 miliardach parametrów, zaprojektowany specjalnie do obsługi długiego ogona w autonomicznej jeździe, wagi są dostępne na licencji Linux Foundation OpenMDW-1.1, kod na licencji Apache 2.0, gotowy do użytku komercyjnego od pierwszego dnia wydania.","category":"模型更新","source":"MarkTechPost（RSS）","aggregationSource":"MarkTechPost（RSS）","pageTitle":"NVIDIA wprowadza Alpamayo 2 Super: 34-miliardowy otwarty model wizualno-językowo-ruchowy dla Robotaxi i autonomicznej jazdy - Aioga Wiadomości AI","description":"NVIDIA ogłosiła Alpamayo 2 Super, model wizualno-językowo-ruchowy (VLA) o 34 miliardach parametrów, zaprojektowany specjalnie do obsługi długiego ogona w autonomicznej jeździe, wag...","url":"https://www.aioga.com/pl/news/cmsfu19g30eg5rochm0d4q3po/","contentTranslated":true,"sourceHash":"9ee1b9523145a131","translatedAt":"2026-08-05T11:11:45.443Z"}}}}