{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-07-23T08:01:28.298Z","headline":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","description":"小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","url":"https://www.aioga.com/news/cmrug2xmi01a4bi6xqh5re996/","mainEntityOfPage":"https://www.aioga.com/news/cmrug2xmi01a4bi6xqh5re996/","datePublished":"2026-07-21T08:56:51.000Z","dateModified":"2026-07-21T08:56:51.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://the-decoder.com/xiaomi-robotics-1-shows-that-more-data-beats-bigger-models-when-training-robots-to-move","https://aihot.virxact.com/items/cmrug2xmi01a4bi6xqh5re996"],"canonicalUrl":"https://www.aioga.com/news/cmrug2xmi01a4bi6xqh5re996/","directAnswer":{"@type":"Answer","text":"Aioga 编辑摘要：小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。 Aioga 将其归入「论文研究」方向，重点关注它对真实使用和行业竞争的影响。","url":"https://www.aioga.com/news/cmrug2xmi01a4bi6xqh5re996/","dateCreated":"2026-07-21T08:56:51.000Z","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":"the-decoder.com source article","url":"https://the-decoder.com/xiaomi-robotics-1-shows-that-more-data-beats-bigger-models-when-training-robots-to-move","datePublished":"2026-07-21T08:56:51.000Z","provider":{"@type":"Organization","name":"the-decoder.com","url":"https://the-decoder.com/xiaomi-robotics-1-shows-that-more-data-beats-bigger-models-when-training-robots-to-move"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmrug2xmi01a4bi6xqh5re996","datePublished":"2026-07-21T08:56:51.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmrug2xmi01a4bi6xqh5re996"}}],"aggregationSource":"The Decoder：AI News（RSS）","originalPublisher":{"name":"the-decoder.com","url":"https://the-decoder.com/xiaomi-robotics-1-shows-that-more-data-beats-bigger-models-when-training-robots-to-move"},"article":{"id":"cmrug2xmi01a4bi6xqh5re996","slug":"cmrug2xmi01a4bi6xqh5re996","url":"https://www.aioga.com/news/cmrug2xmi01a4bi6xqh5re996/","title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","title_en":"Xiaomi-Robotics-1 shows that more data beats bigger models when training robots to move","summary":"小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","source":"The Decoder：AI News（RSS）","sourceUrl":"https://the-decoder.com/xiaomi-robotics-1-shows-that-more-data-beats-bigger-models-when-training-robots-to-move","aiHotUrl":"https://aihot.virxact.com/items/cmrug2xmi01a4bi6xqh5re996","publishedAt":"2026-07-21T08:56:51.000Z","category":"论文研究","score":42,"selected":false,"articleBody":["Xiaomi has released an AI model for robots that follows the same scaling pattern as large language models. Its performance improves as it trains on more data. To build that dataset, Xiaomi largely avoided using physical robots.","Robot AI faces a data problem that language models don't: LLMs can train on huge parts of the public internet, while useful data on robot movement is scarce. Robots usually have to learn from scratch how to grip, lift, and put away objects. The standard method has people remotely guide a physical robot through every movement. That process is slow and expensive, and it often produces repetitive data from the same tasks in the same settings.","That's the gap Xiaomi-Robotics-1 is trying to close：https://github.com/XiaomiRobotics/Xiaomi-Robotics-1. The model is designed to follow spoken or written commands in unfamiliar environments without prior exposure and adapt to new tasks with little extra training.","To get around the data bottleneck, Xiaomi mostly ditched real robots during data collection. Instead, the team used portable handheld grippers with attached cameras that a person simply picks up and operates by hand. This setup lets you record manipulation tasks in kitchens, offices, stores, factory floors, and outdoor spaces without a robot even being present. The result was over 100,000 hours of motion recordings.","A dataset that large creates another problem because each recording needs a description the model can learn from. Labeling it all by hand wasn't practical, so Xiaomi used another AI model to describe each motion segment in text. The team says it labeled the full dataset in about two weeks.","Xiaomi then transferred that training to physical robots, including wheeled models and dual-arm systems. The model still had to account for the differences between a handheld gripper and a robot arm.","Tests showed that a larger model improved performance, but more training data produced much bigger gains than more compute. The researchers say progress in robot AI will depend mainly on collecting larger and more varied datasets.","The finding matches what researchers showed for visual data in early March：https://the-decoder.com/llm-text-data-is-drying-up-but-meta-points-to-unlabeled-video-as-the-next-massive-training-frontier/. For language models, the long-standing rule is that model size and data volume should grow at roughly the same rate：https://arxiv.org/abs/2203.15556 to make the best use of a fixed compute budget. That balance changes when a model must process images rather than just text. In that case, adding data helps far more than increasing model size.","The same pattern appeared in tests with physical robots. As Xiaomi increased the amount of training data, the model's success rate in unfamiliar environments rose from about 25 percent to 75 percent. The researchers say they haven't reached a point where more data stops improving performance.","Xiaomi says Xiaomi-Robotics-1 posted the best results to date across standard robot AI benchmarks. In one demo, a robot reportedly packed a suitcase without human help. The task took more than ten minutes and required the robot to move across an entire room.","A foundation model is most useful when it can adapt to new tasks quickly. Xiaomi tested Xiaomi-Robotics-1 on four tasks, including packaging a phone, loading laundry into a washing machine, feeding paper into a printer, and packing items into a box.","With less than ten hours of training data for each task, the model reached an average success rate of 75 percent. A competing model from Physical Intelligence managed only 40 percent in the same test. Xiaomi says its model performed especially well with soft, deformable materials such as paper and on tasks that required moving around a room.","Robot data remains a major focus of robotics research, and teams are pursuing very different solutions. A May survey of World Action Models：https://the-decoder.com/world-action-models-give-robots-the-ability-to-simulate-consequences-before-they-move/ reviewed about 100 studies and found that teleoperation data is precise but costly and limited to a few settings. Xiaomi's handheld grippers are designed to address those limits.","Nvidia, Carnegie Mellon University, and UC Berkeley used the ENPIRE project to have AI coding agents autonomously teach a fleet of eight robots how to grasp objects：https://the-decoder.com/nvidia-research-shows-robots-that-train-themselves-through-ai-coding-agents/. Nvidia also wants to turn robotics' data problem into a compute problem：https://the-decoder.com/gtc-2026-nvidia-wants-to-swap-robotics-data-problem-for-a-compute-problem/ by generating synthetic training data.","China's BAAI research institute is taking the opposite route. Its Orca world model learns from 125,000 hours of video without any action labels：https://the-decoder.com/chinas-orca-world-model-matches-specialized-robotics-systems-without-ever-seeing-a-single-action-label/ and still matches the specialized pi0.5 model on five manipulation tasks. Xiaomi automates labeling and applies it at scale, while Orca tries to eliminate labels entirely.","Physical Intelligence serves as the reference point in both cases. The company drew criticism for pi0.7 in April：https://the-decoder.com/physical-intelligence-shows-robot-model-with-llm-like-generalization-flaws-included/ after claiming the model could generalize when it may have been recalling similar training data. Xiaomi's finding that more data matters more than more compute makes that question harder to resolve.","The work also fits Xiaomi's broader plans. When the company introduced its MiMo-V2 models in March：https://the-decoder.com/xiaomi-launches-three-mimo-ai-models-to-power-agents-robots-and-voice/, it said those agents could eventually control robots.","Xiaomi plans to release the model and code on GitHub：https://github.com/XiaomiRobotics/Xiaomi-Robotics-1 and Hugging Face：https://huggingface.co/XiaomiRobotics. The same team recently released Xiaomi-Robotics-0 as open source, with a focus on fast, real-time operation.","Stay in the loop on AI. Clear, useful, no fluff.","Follow The Decoder for AI news, background stories and expert analyses.","The Decoder：https://the-decoder.com/"],"articleImages":[{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/07/xiaomi-robotics-1-01-hero.jpg","alt":"Image description","afterParagraph":0,"url":"/media/articles/cmrug2xmi01a4bi6xqh5re996/efba59f62aa73752.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/07/xiaomi-robotics-1-02-pretrain-data.jpg","alt":"Overview of the pretraining dataset showing camera footage from households, offices, industrial sites, restaurants, commercial spaces, and outdoor settings, with key figures: 100K hours, 1.7K scenarios, 2.4M episodes, and 260+ tasks, plus word clouds for objects and verbs.","afterParagraph":3,"url":"/media/articles/cmrug2xmi01a4bi6xqh5re996/4a76e4367d1d1dbc.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/07/xiaomi-robotics-1-03-posttrain-data.jpg","alt":"Three-part overview of post-training data showing in-house robot recordings, renderings of a mobile manipulator and dual-arm robot, open-source robot data, and UMI data with instruction labels.","afterParagraph":5,"url":"/media/articles/cmrug2xmi01a4bi6xqh5re996/e05d1d74d3e8b03c.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/07/xiaomi-robotics-1-04-pretrain-scaling.jpg","alt":"Two line charts showing Validation Action Error (MSE) over training steps, with the left chart scaling by data volume from 12.5 to 100 percent and the right chart scaling by model size from 2B to 10B parameters.","afterParagraph":7,"url":"/media/articles/cmrug2xmi01a4bi6xqh5re996/cf11eaf73ed53156.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/07/xiaomi-robotics-1-05-posttrain-scaling.jpg","alt":"Two bar charts showing success rates in percent for shoe storage, bag packing, table organization, and sofa tidying tasks, broken down by pretraining data percentage and by model size.","afterParagraph":8,"url":"/media/articles/cmrug2xmi01a4bi6xqh5re996/52e8222caa5561a2.jpg"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/07/xiaomi-robotics-1-06-robocasa365-leaderboard.jpg","alt":"RoboCasa365 leaderboard table showing Xiaomi-Robotics-1 in first place with 57.4 points, ahead of ABot-M0.6 at 46.6 and ABot-M0.5 at 40.3.","afterParagraph":11,"url":"/media/articles/cmrug2xmi01a4bi6xqh5re996/75542068a65e4f05.jpg"}],"mediaStatus":"ok","articleBodyZh":["小米发布了一个用于机器人的人工智能模型，其扩展模式与大型语言模型相同。随着训练数据的增加，其性能会提升。为了构建该数据集，小米在很大程度上避免使用实体机器人。","机器人 AI 面临一个语言模型没有的数据问题：大型语言模型可以在互联网上的海量公开数据上进行训练，而关于机器人运动的有用数据却很稀缺。机器人通常需要从零开始学习如何抓取、搬运和放置物品。标准方法是让人远程指导实体机器人完成每一个动作。这个过程既慢又昂贵，而且通常会在相同环境的相同任务中产生重复数据。","这就是 Xiaomi-Robotics-1 试图弥补的差距：https://github.com/XiaomiRobotics/Xiaomi-Robotics-1。该模型被设计为在不熟悉的环境中遵循口头或书面指令，并能通过少量额外训练适应新任务。","为了绕过数据瓶颈，小米在数据收集过程中基本上放弃了真实机器人。相反，团队使用了带有摄像头的便携手持抓手，人只需拿起并手动操作。这种设置可以在厨房、办公室、商店、工厂车间和户外空间记录操作任务，而无需机器人在场。最终获得了超过 10 万小时的运动记录。","如此大的数据集又带来了另一个问题，因为每段记录都需要模型可以学习的描述。完全手工标注不可行，因此小米使用了另一种 AI 模型来将每段运动记录转换为文本描述。团队表示，他们约在两周内完成了整个数据集的标注。","随后，小米将这些训练迁移至实体机器人，包括轮式模型和双臂系统。模型仍需考虑手持抓手与机器人手臂之间的差异。","测试表明，较大的模型提升了性能，但更多的训练数据带来的增益远大于更多的计算资源。研究人员表示，机器人 AI 的进展主要依赖于收集更大、更丰富的数据集。","这一发现与研究人员在三月初对视觉数据的展示一致：https://the-decoder.com/llm-text-data-is-drying-up-but-meta-points-to-unlabeled-video-as-the-next-massive-training-frontier/。对于语言模型来说，长期以来的规则是模型规模和数据量应大致以相同的速度增长：https://arxiv.org/abs/2203.15556，以在固定计算预算下实现最佳利用。当模型必须处理图像而不仅仅是文本时，这种平衡会发生变化。在这种情况下，增加数据的帮助远大于增加模型规模。","在与物理机器人进行的测试中也出现了相同的模式。随着小米增加训练数据量，模型在陌生环境中的成功率从约25%上升至75%。研究人员表示，他们尚未达到数据增加不再提升性能的程度。","小米表示，小米机器人1号在标准机器人AI基准测试中取得了迄今为止的最佳成绩。在一次演示中，据称机器人无需人工帮助就完成了整理行李的任务。该任务耗时超过十分钟，并要求机器人在整个房间内移动。","当基础模型能够快速适应新任务时，它最为有用。小米在四项任务上测试了小米机器人1号，包括包装手机、将衣物放入洗衣机、将纸张送入打印机以及将物品装入箱子。","在每项任务的训练数据少于十小时的情况下，模型达到了平均75%的成功率。来自Physical Intelligence的竞争模型在同一测试中仅达到40%。小米表示，其模型在处理纸张等柔软、易变形的材料以及需要在房间内移动的任务时表现特别出色。","机器人数据仍然是机器人研究的主要关注点，各团队正在追求非常不同的解决方案。五月份关于世界行动模型的调查：https://the-decoder.com/world-action-models-give-robots-the-ability-to-simulate-consequences-before-they-move/ 回顾了约100项研究，发现遥操作数据精确但成本高，并且仅限于少数环境。小米的手持抓取器旨在解决这些限制。","英伟达、卡内基梅隆大学和加州大学伯克利分校利用 ENPIRE 项目让 AI 编码代理自主教授八台机器人如何抓取物体：https://the-decoder.com/nvidia-research-shows-robots-that-train-themselves-through-ai-coding-agents/。英伟达还希望通过生成合成训练数据，将机器人学的数据问题转化为计算问题：https://the-decoder.com/gtc-2026-nvidia-wants-to-swap-robotics-data-problem-for-a-compute-problem/。","中国的 BAAI 研究院则走了相反的路线。其 Orca 世界模型通过 125,000 小时的视频学习，无需任何动作标签：https://the-decoder.com/chinas-orca-world-model-matches-specialized-robotics-systems-without-ever-seeing-a-single-action-label/，并且在五个操作任务中仍然能够匹配专业的 pi0.5 模型。小米实现了标签自动化并大规模应用，而 Orca 则尝试完全消除标签。","Physical Intelligence 在这两种情况下都作为参考点。该公司在四月份因为 pi0.7 而受到批评：https://the-decoder.com/physical-intelligence-shows-robot-model-with-llm-like-generalization-flaws-included/，有人认为该模型可能是在回忆相似的训练数据，而不是实现真正的泛化。小米发现更多数据比更多计算更重要，这使得这个问题更难解决。","这项工作也符合小米的更广泛计划。当公司在三月推出 MiMo-V2 模型时：https://the-decoder.com/xiaomi-launches-three-mimo-ai-models-to-power-agents-robots-and-voice/，表示这些代理最终可以控制机器人。","小米计划在 GitHub：https://github.com/XiaomiRobotics/Xiaomi-Robotics-1 和 Hugging Face：https://huggingface.co/XiaomiRobotics 上发布模型和代码。同一团队最近发布了 Xiaomi-Robotics-0 开源版本，重点是快速、实时操作。","保持对 AI 的关注。清晰、有用，无花哨。","关注 The Decoder 获取 AI 新闻、背景故事和专家分析。","The Decoder：https://the-decoder.com/"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"Aioga 编辑摘要：小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。 Aioga 将其归入「论文研究」方向，重点关注它对真实使用和行业竞争的影响。","background":"背景分析：模型与研究类动态需要结合能力边界、开放方式、成本、可用性和真实任务表现判断，单项指标领先不等于已经形成稳定采用。","viewpoint":"Aioga 判断：这条动态更适合作为行业观察信号，当前信息足以建立线索，但不足以推导长期结论。","implications":"影响分析：对相关团队而言，短期应先核对来源、可用范围和实际成本，再判断是否值得接入或跟进。","nextStep":"后续观察：继续观察官方文档、实际可用性、价格变化、开发者反馈和竞品回应。","evidenceRefs":["title","summary","articleBody"],"confidence":"medium","status":"published","aiGenerated":false,"autoApproved":true,"generatedBy":"rule-safe-fallback","generatedAt":"2026-07-23T08:10:16.728Z","sourceHash":"5046bd0e0a727480","validation":{"passed":true,"mode":"rule-safe-fallback","checks":["schema","length","source-attribution","no-html"]}},"tags":["论文研究","The Decoder：AI News（RSS）"],"translations":{"zh-CN":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga AI资讯","description":"小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","url":"https://www.aioga.com/news/cmrug2xmi01a4bi6xqh5re996/"},"en":{"title":"Xiaomi-Robotics-1 shows that more data beats bigger models when training robots to move","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under Research. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"Research","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Xiaomi-Robotics-1 shows that more data beats bigger models when training robots to move - Aioga AI News","description":"Aioga tracks this update from The Decoder：AI News（RSS） under Research. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能...","url":"https://www.aioga.com/en/news/cmrug2xmi01a4bi6xqh5re996/"},"ja":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aiogaは「論文研究」の動きとして、The Decoder：AI News（RSS） からの更新を追跡しています。小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"論文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga AIニュース","description":"Aiogaは「論文研究」の動きとして、The Decoder：AI News（RSS） からの更新を追跡しています。小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌...","url":"https://www.aioga.com/ja/news/cmrug2xmi01a4bi6xqh5re996/"},"ko":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga는 The Decoder：AI News（RSS）의 업데이트를 연구 흐름으로 추적합니다. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"연구","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga AI 뉴스","description":"Aioga는 The Decoder：AI News（RSS）의 업데이트를 연구 흐름으로 추적합니다. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中...","url":"https://www.aioga.com/ko/news/cmrug2xmi01a4bi6xqh5re996/"},"es":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga sigue esta actualización de The Decoder：AI News（RSS） dentro de Investigación. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"Investigación","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga Noticias de IA","description":"Aioga sigue esta actualización de The Decoder：AI News（RSS） dentro de Investigación. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显...","url":"https://www.aioga.com/es/news/cmrug2xmi01a4bi6xqh5re996/"},"fr":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga suit cette mise à jour de The Decoder：AI News（RSS） dans la catégorie Recherche. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"Recherche","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga Actualités IA","description":"Aioga suit cette mise à jour de The Decoder：AI News（RSS） dans la catégorie Recherche. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测...","url":"https://www.aioga.com/fr/news/cmrug2xmi01a4bi6xqh5re996/"},"de":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga KI-News","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/de/news/cmrug2xmi01a4bi6xqh5re996/"},"pt-BR":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga Notícias de IA","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/pt-BR/news/cmrug2xmi01a4bi6xqh5re996/"},"ru":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga Новости ИИ","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/ru/news/cmrug2xmi01a4bi6xqh5re996/"},"ar":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga أخبار الذكاء الاصطناعي","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/ar/news/cmrug2xmi01a4bi6xqh5re996/"},"hi":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga AI समाचार","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/hi/news/cmrug2xmi01a4bi6xqh5re996/"},"it":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga Notizie IA","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/it/news/cmrug2xmi01a4bi6xqh5re996/"},"nl":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga AI-nieuws","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/nl/news/cmrug2xmi01a4bi6xqh5re996/"},"tr":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga AI Haberleri","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/tr/news/cmrug2xmi01a4bi6xqh5re996/"},"vi":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Tin tức AI Aioga","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/vi/news/cmrug2xmi01a4bi6xqh5re996/"},"id":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Berita AI Aioga","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/id/news/cmrug2xmi01a4bi6xqh5re996/"},"th":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - ข่าว AI Aioga","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/th/news/cmrug2xmi01a4bi6xqh5re996/"},"pl":{"title":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超扩大模型规模，在陌生环境中成功率从约25%升至75%，并在标准机器人AI基准测试中取得最佳成绩。","category":"论文研究","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"小米发布机器人AI模型Xiaomi-Robotics-1：更多训练数据比更大模型更有效 - Aioga Wiadomości AI","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. 小米发布机器人AI模型Xiaomi-Robotics-1，其性能随训练数据量提升而增长。团队使用便携手持夹持器替代实体机器人采集了超10万小时运动数据，并用AI模型在两周内完成全部标注。测试显示，增加训练数据带来的性能提升远超...","url":"https://www.aioga.com/pl/news/cmrug2xmi01a4bi6xqh5re996/"}}}}