搜索“NVIDIA”

s with emptied context helps them escape “idea basins.” At equal compute it beats single runs and best-of-N on 12 of 13 long-horizon tasks (@DimitrisPapail). Other results: LoGRA (NVIDIA): Full-weight RL that uses less memory than LoRA, 7.2 GiB against 13.2 GiB at 1.5B (@omarsar0). nanoswe: A 1.7B coding agent trained from scratch for about $1,000 of compute scores 25.5% on SWE-bench Verified (@rdolmedo ). Test-writing gap: Frontier agents’ tests catch fewer than 55% of logical mutants (@nielstr

匹配字段正文

Five-year commitment targets AI and scientific research capabilities JEONG IL JOO; Published 2026.10.13 14:28; Reply 0 Nvidia announced Oct. 12 that it will invest $1 billion over the next five years to build superintelligence capabilities and strengthen scientific research in the United States. Nvidia Founder and Chief Executive Officer (CEO) Jensen Huang said at the "Science: The New Golden Age" event in Washington, D.C., on Oct. 8 that the investment would give U.S. scientists access to advan

匹配字段正文

y Data Processing Units (DPUs), graphics processing unit (GPU) servers, storage servers, and networking technology help cut infrastructure costs and boost operational efficiency. "Nvidia and MangoBoost are the only companies with this kind of business model," Kim added. MangoBoost is also expanding its data center infrastructure to support Mango Inference. It plans to establish a 1-megawatt (MW) AI data center in Gangnam District, Seoul, by the first quarter of next year, with plans to expand ca

匹配字段正文

the kernel already tracks usage per container for you, so getting a per-pod number is basically free. GPUs on the other hand, don’t give you that. The tool everybody starts with, NVIDIA’s DCGM exporter, reports at the physical device level by default. This is fine when one pod has a GPU to itself, but the second you start sharing a GPU across pods, with time-slicing or MPS, DCGM gives every pod sharing that GPU the same value. So if three pods are sharing one GPU, all three look like they’re us

匹配字段正文

atistical analysis, machine learning, and data engineering, Michal excels at transforming complex datasets into actionable insights. Michal SutterWhat is Decision 3.0? vLLM Semantic Router’s New Open Decision Models; Michal SutterMeet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling; Michal SutterArchitect Launches Liquid Inference, a Real-Time Auction for LLM Inference; Michal SutterNVIDIA PivotOPD Teaches Multi-Turn AI Agents to Recover From Pivotal Mistakes

匹配字段正文

gentic Infra） 战略布局，贯通算力资源、Token生产与行业应用三层价值链。 其中，“一中心”是算力集散中心，即Agentic Infra自主式基础设施平台。目前该平台已部署算力达37000P，覆盖16种主流芯片。无问芯穹此前发布了全球首个千卡规模异构芯片混训平台，具备万卡扩展性，已实现华为昇腾、天数智芯、沐曦、摩尔线程四种国产芯片分别与AMD、NVIDIA两种进口芯片进行大模型混合训练，算力利用率最高达到97.6%。 “后厂”是Token工厂，对应智能体模型即服务 （Agentic MaaS） 大模型服务平台。今年7月，无问芯穹在世界人工智能大会上发布了新一代推理系统优化成果——跨集群异构PD分离架构 （PDD） ，基于Agentic MaaS线上业务长期大规模的实践积淀，该架构在实现了首Token延迟 （TTFT） 降低51.5%的同时，单Token成本可降低37.5%。过去一年里，无问芯穹的Token工厂已通过一系列原始技术创新，推动推理成本降至原来的十分之一，截至7月，无问芯穹Agentic MaaS平台单日Token调用量较去年12月实现了40倍增长。 “前店”是

匹配字段正文

产芯片不断发展，算力供给逐渐呈现多元化，新的问题随之出现：不同品牌、不同架构的芯片如何协同工作？如何将分散的算力资源转化为稳定、高效、可持续使用的模型训练与推理能力？ 这正是无问芯穹团队长期深耕的方向。公开资料显示，无问芯穹在2024年便完成了全球首次“4+2”式700亿参数大模型异构芯片混合训练，运用华为昇腾、天数智芯、沐曦、摩尔线程四种国产芯片与AMD、NVIDIA两种进口芯片，算力利用率达97.6%。 目前其已可以实现2个工作日完成新芯片适配，国产芯片适配成本降低70%以上；在万亿参数级MoE模型训练中，其吞吐较主流开源框架提升41%至75%，在推理上更是实现成本一年内下降10倍。 这些指标的背后，是团队从实验室到产业一线，始终深耕多元异构与软硬件协同创新的技术积累。 从长期看，国产化与算力供给多元化、碎片化，将使异构协同成为持续性的产业需求。无问芯穹提前围绕“M种模型×N种芯片”构建技术体系，恰好覆盖了这一长期需求。 这种先发优势，让它在国产异构布局中占据了有利位置。 二、前店后厂一中心：不碰模型不碰芯片，中立平台卡位Token需求爆发 随着Agent应用加速发展，AI基础设施

匹配字段正文

calls for global rules on AI, and says the UK is in the "best position" to lead the charge. At the end of last month, Trump hosted the leaders of US tech giants OpenAI, Anthropic, Nvidia, SpaceX, Meta, and Google at the White House where the executives signed a "morally binding" document. The companies agreed to work with "independent auditors" to assess whether their AI systems are working as intended and make sure they do not "hack or access technical systems in unintended ways". Smith said he

匹配字段正文

and data engineering, Michal excels at transforming complex datasets into actionable insights. Michal SutterMeet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling; Michal SutterArchitect Launches Liquid Inference, a Real-Time Auction for LLM Inference; Michal SutterNVIDIA PivotOPD Teaches Multi-Turn AI Agents to Recover From Pivotal Mistakes; Michal SutterAnthropic Releases Claude Haiku 5.5: A Small Model With 1M Context Priced at $0.10 per Million Input Tokens

匹配字段正文

FT just reported Nvidia is in early talks to acquire, or invest further in, Reflection AI, a $25B open-weight model start-up. One option is an acqui-hire, in which Nvidia hires Reflection’s staff and licenses its technology without the antitrust review a full takeover would trigger. Nvidia used that structure for its $20B Groq deal last December, and a deal could come within weeks, though the talks could still fall apart. Nvidia is already one of Reflection’s largest shareholders after investing

匹配字段正文

n and angle 120 times a second with about 10ms delay or less, and software turns that into joint angles the robot hand copies. A 526-point pressure grid on the glove's palm also records how hard the person grips, which makes it useful for collecting training data for robots that learn by copying humans. WUJI released the code, motion clips, trained models and printable pen files under the open Apache 2.0 license, so a lab with a WUJI Hand 2, a camera and an NVIDIA GPU can repeat the whole setup.

匹配字段正文

raction of compute, with the majority being employed for large-scale RL on synthetic and human-created environments. Inkling was our first major training effort and was trained on NVIDIA GB300 NVL72 systems. Future models will further push the scale of compute across pre-training, post-training and RL. RL at scale We relied on large-scale asynchronous RL to shape model behavior and improve its reasoning and overall performance. The chart below shows the model’s score on a held-out aggregate of r

匹配字段正文

odel that achieves comparable performance to Inkling at a quarter of its size. Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable thinking effort, a context window of up to 1M tokens, and well-rounded performance across a range of benchmarks. Inkling-Small Inkling Compared to Inkling, Inkling-Small achieves comparable performance with much less

匹配字段正文

updated weights, and those weights return to serving for the next round. Slow checkpoint loading slows the whole cycle. Our new RL rollouts feature in Dedicated Inference uses the NVIDIA Dynamo foundation to hot-load updated checkpoints with minimal downtime. We partnered with NVIDIA and you.com’s engineering team to post-train NVIDIA Nemotron 3.5 Lightning using RL Rollouts in NeMo gym with you.com’s web search application programming interface (API). Our launch post reports a 15-fold improveme

匹配字段正文

ccording to Beard, developers can use Standard Bots’ APIs to build robotics applications with whichever parts of its stack they need, including bringing their own models. He cited NVIDIA Cosmos, an open family of omnimodal world models for physical AI, as an example (version 3 was released late-May). Today, this requires developers to write their own integration code. But Standard Bots plans to make collecting data, training models, and deploying them onto its robots easier. Focus on targeted da

匹配字段正文

ccording to Beard, developers can use Standard Bots’ APIs to build robotics applications with whichever parts of its stack they need, including bringing their own models. He cited NVIDIA Cosmos, an open family of omnimodal world models for physical AI, as an example (version 3 was released late-May). Today, this requires developers to write their own integration code. But Standard Bots plans to make collecting data, training models, and deploying them onto its robots easier. Focus on targeted da

匹配字段正文

complex reasoning AFM 3 Core, AFM 3 Core Advanced, and AFM 3 Cloud, along with ADM 3 Cloud, are all purpose-built for Apple silicon. For AFM 3 Cloud Pro, we worked with Google and NVIDIA to extend Private Cloud Compute to NVIDIA GPUs in Google Cloud, while maintaining the same guarantees to protect our users’ privacy. More details are available on our Security Research Website. Our third generation of Apple Foundation Models delivers significant advancements across capabilities and quality. In t

匹配字段正文

密的前提下促进高价值数据流通；推动公共数据底座建设。 产业侧的动作已经开始。解耦层面：鹿明机器人的 FastUMI 与本体解耦，适配市面 90% 以上机械臂；光轮智能的 RoboFinals 支持异构本体接入。标准层面：光轮智能是 Newton 仿真技术指导委员会唯一中国企业，参与 EgoVerse 人类数据委员会，主导或参编 20 项国家及行业标准，并与 NVIDIA 共同定义 SimReady 标准。流通层面：觅蜂数据商城、库帕思、百度数据平台以及北京／上海／深圳数据交易所，构成了交易平台的第一批供给；北京人形机器人创新中心推动公共数据底座与标准制定。 结语 “造治用通”四个字，本质上回答的是同一个问题： 数据如何从一次性消耗品变成可积累、可复售、可增值的资产。 造数据解决供给，治数据解决质量，转飞轮解决增值，通数据解决流动。四者缺一环，行业就会回到“采得少、训不好、用不了”的低水平循环。 中国具身数据产业链生态体系正在快速发展与完善中，商业机会巨大，更多板块详细分析 ， 请关注易 观分析 近期发布 的 《中国具身智能数据产业分析报告2026》。 易观分析将及时更新《中国 具身数据

匹配字段正文

f hectares of forest had been cleared without required environmental reviews. Microsoft opened preorders for its Surface Laptop Ultra, starting at $2,599 and arriving Oct.16, with Nvidia hardware designed to run powerful AI models locally. Anduril landed a Navy contract worth up to $2.9B for submarine production and plans a $3.7B shipyard, days after Palmer Luckey joined a Pentagon weapons advisory group. Rivian R2 owners can watch pets left inside their parked car via live video in the app or u

匹配字段正文

类示范采集，SimFoundry负责仿真生成， 其定位不是单一路线的数据商，而是物理 AI 的数据与评测基础设施 。 图 3：中国具身数据市场发展的三线协同 2. 物理引擎 ×生成式AI 重定义 仿真数据 上限 引擎的物理正确性是仿真数据能否迁移到真机的底线，生成式 AI的自动化生成解 决了 人工建模的规模瓶颈。光轮智能自研高精度 GPU物理求解器， 参与 NVIDIA Newton 仿真技术 指导 委员会， 并与 NVIDIA共同定义SimReady 资产 规范 ，支持 PhysX／MuJoCo／Newton／GENESIS多种引擎；无问智科把SimReady资产构建从3天压缩到5分钟（300倍），柔性物体相关性达90%、接触误差小于1%；群核科技则用十余年沉淀的5亿+结构化3D场景、4.8亿带物理参数的3D模型，把渲染空间批量转成物理正确的三维表示。三家的共同点是：先把 “ 物理正确 ” 这件事做硬，再谈生成规模。 3. 无本体采集承接人类操作数据入口 以 “人持 / 穿戴设备采操作”绕开真机遥操作的高成本与本体硬件依赖，在真实物理环境中获取带时序对齐、体感细节的人类行为数据。定位

匹配字段正文