{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-07-23T08:01:28.298Z","headline":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","description":"Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","url":"https://www.aioga.com/news/cmrj0wvrs04lcbilk41ofc7q5/","mainEntityOfPage":"https://www.aioga.com/news/cmrj0wvrs04lcbilk41ofc7q5/","datePublished":"2026-07-13T09:16:48.000Z","dateModified":"2026-07-13T09:16:48.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://the-decoder.com/sensorfm","https://aihot.virxact.com/items/cmrj0wvrs04lcbilk41ofc7q5"],"canonicalUrl":"https://www.aioga.com/news/cmrj0wvrs04lcbilk41ofc7q5/","directAnswer":{"@type":"Answer","text":"Aioga 编辑摘要：Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。 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/cmrj0wvrs04lcbilk41ofc7q5/","dateCreated":"2026-07-13T09:16:48.000Z","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/sensorfm","datePublished":"2026-07-13T09:16:48.000Z","provider":{"@type":"Organization","name":"the-decoder.com","url":"https://the-decoder.com/sensorfm"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmrj0wvrs04lcbilk41ofc7q5","datePublished":"2026-07-13T09:16:48.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmrj0wvrs04lcbilk41ofc7q5"}}],"aggregationSource":"The Decoder：AI News（RSS）","originalPublisher":{"name":"the-decoder.com","url":"https://the-decoder.com/sensorfm"},"article":{"id":"cmrj0wvrs04lcbilk41ofc7q5","slug":"cmrj0wvrs04lcbilk41ofc7q5","url":"https://www.aioga.com/news/cmrj0wvrs04lcbilk41ofc7q5/","title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","title_en":"Google's SensorFM turns messy wearable sensor data into a general-purpose health intelligence layer","summary":"Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","source":"The Decoder：AI News（RSS）","sourceUrl":"https://the-decoder.com/sensorfm","aiHotUrl":"https://aihot.virxact.com/items/cmrj0wvrs04lcbilk41ofc7q5","publishedAt":"2026-07-13T09:16:48.000Z","category":"论文研究","score":41,"selected":false,"articleBody":["Google Research has unveiled SensorFM, a foundation model that learns a general representation of human physiology and behavior from wearable sensor data collected from five million people. The model can be applied to 35 different health and behavioral tasks.","Most health features on wearables today are built for a single purpose. One model detects sleep stages, another estimates cardiovascular risk, and yet another analyzes stress or metabolic markers. Google wants to replace these siloed approaches with a shared AI foundation that can make sense of continuous, often gappy sensor data across many health questions, cut the need for expensive labeled training data, and eventually feed personalized context into AI health assistants.","Google Research has now introduced SensorFM in a blog post and an accompanying paper. The foundation model learns a general, reusable representation of physiological and behavioral patterns from large volumes of unlabeled wearable data. The researchers used more than a trillion minutes of multimodal sensor data from five million Fitbit and Pixel Watch users for pretraining. The data came from over 100 countries and was collected with more than 20 different Fitbit and Pixel Watch models. According to the authors, this is the largest and most diverse wearable dataset ever used to train a model of this kind. Ad","SensorFM processes 34 features drawn from five types of sensor data: optical heart rate monitoring (photoplethysmography, or PPG), acceleration, skin conductance, skin temperature, and barometric altitude. The features include heart rate, heart rate variability, blood oxygen saturation, sleep stages, and motion data, among others. The model is trained in a self-supervised way by reconstructing deliberately masked data segments. The technique, called \"Adaptive and Inherited Masking\" (AIM), flags both genuinely missing values and values that were artificially hidden during training, so SensorFM learns to handle both types of data gaps. Ad DEC_D_Incontent-1","The researchers report that performance improves systematically when model size and data volume grow together. The four model variants they tested range from about 100,000 to 100 million parameters, and the training datasets span from 5,000 to five million people. On the largest training dataset, the biggest model's reconstruction error was 31 percent lower than the smallest model's. The largest configuration also performed best on most downstream prediction tasks.","The researchers then tested SensorFM on data from three separate studies with a total of 13,985 participants. The model had never seen this data during pretraining. They evaluated SensorFM on 35 prediction tasks covering cardiovascular and metabolic health, mental health, sleep, demographics, and lifestyle. Ad","Even simple task-specific head models built on top of SensorFM's learned representations outperformed supervised baselines with hand-crafted wearable features on 34 of 35 tasks, according to the paper. Scaled pretraining also made SensorFM more label-efficient compared to the supervised baselines. The model could adapt to new tasks with relatively few labeled examples, and as it grew larger, it relied less on extra demographic information. The authors believe scaled pretraining could be especially useful for hard-to-measure traits that vary widely between individuals, such as depression and anxiety symptoms.","To adapt SensorFM's learned representations to new tasks, the researchers set up a \"classroom\" of competing and collaborating LLM agents. These agents repeatedly generated, tested, and refined code for downstream prediction models, running more than 30,000 experiments in the process. The models they found outperformed simple linear head models based on the same SensorFM representations on 28 of 35 prediction tasks. Ad DEC_D_Incontent-2","The researchers also integrated SensorFM into a personal health agent and compared three variants. All three received demographic information and daily summaries computed from wearable data, covering things like activity, sleep, blood oxygen, and skin temperature. One variant also received SensorFM predictions for various health markers, a second received the actual known values for those same markers, and the third got none of this extra information and served as the baseline. Ad","Four clinicians evaluated 93 health summaries for 31 real participant profiles, spending more than 40 hours and producing 1,860 individual ratings. The result: summaries augmented with SensorFM predictions scored significantly higher than the baseline across all five dimensions the team measured, which were context, personalization, justifiability, relevance, and safety. There was no statistically significant difference overall between summaries that used SensorFM predictions and those that used actual known health data. That said, this doesn't mean SensorFM can replace clinical measurements or diagnoses.","The researchers point to several limitations. SensorFM was trained and tested only on data from Fitbit and Pixel Watch devices. Whether the results transfer to other wearables is an open question. The model also doesn't work with high-resolution raw signals but with data aggregated at the minute level, which means very short or fine-grained patterns can get lost.","Many of the health markers the team studied are based on self-reports, medication records, or questionnaires rather than clinically confirmed findings. The study population also doesn't fully represent the general population. And the health agent was only evaluated in a static setup with single responses, not in longer conversations with follow-up questions.","SensorFM is purely a research model for now. Google already offers the Gemini-based Google Health Coach：https://the-decoder.com/with-its-new-ai-health-coach-google-leverages-its-platform-advantage/, which provides personalized tips on fitness, sleep, recovery, and other health topics. SensorFM could eventually serve as a technical foundation for features like these, but Google hasn't announced any concrete plans to integrate it into Fitbit, Pixel Watch, or the AI coach.","More details on SensorFM are available in the Google Research blog post：https://research.google/blog/sensorfm-towards-a-general-intelligence-and-interface-for-wearable-health-data/ and the open-access paper on arXiv：https://arxiv.org/abs/2605.22759.","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/SensorFM-Skalierung.png","alt":"Line chart showing SensorFM's scaling behavior.","afterParagraph":3,"url":"/media/articles/cmrj0wvrs04lcbilk41ofc7q5/390d4fa58eac151a.png"},{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/07/SensorFM-Gesundheitsagent.png","alt":"Diagram of a health agent powered by SensorFM.","afterParagraph":8,"url":"/media/articles/cmrj0wvrs04lcbilk41ofc7q5/349e2870bc10dd1c.png"}],"mediaStatus":"ok","articleBodyZh":[],"translationStatus":"","bodyOrigin":"source-page","editorial":{"summary":"Aioga 编辑摘要：Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。 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":"2026-07-23T08:10:16.999Z","sourceHash":"2ea223ec6ae989fa","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":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga AI资讯","description":"Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorF","url":"https://www.aioga.com/news/cmrj0wvrs04lcbilk41ofc7q5/"},"en":{"title":"Google's SensorFM turns messy wearable sensor data into a general-purpose health intelligence layer","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under Research. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"Research","source":"The Decoder：AI News（RSS）","pageTitle":"Google's SensorFM turns messy wearable sensor data into a general-purpose health intelligence layer - Aioga AI News","description":"Aioga tracks this update from The Decoder：AI News（RSS） under Research. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导","url":"https://www.aioga.com/en/news/cmrj0wvrs04lcbilk41ofc7q5/"},"ja":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","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。Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"論文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - 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。Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 3","url":"https://www.aioga.com/ja/news/cmrj0wvrs04lcbilk41ofc7q5/"},"ko":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga는 The Decoder：AI News（RSS）의 업데이트를 연구 흐름으로 추적합니다. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"연구","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga AI 뉴스","description":"Aioga는 The Decoder：AI News（RSS）의 업데이트를 연구 흐름으로 추적합니다. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特","url":"https://www.aioga.com/ko/news/cmrj0wvrs04lcbilk41ofc7q5/"},"es":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga sigue esta actualización de The Decoder：AI News（RSS） dentro de Investigación. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"Investigación","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga Noticias de IA","description":"Aioga sigue esta actualización de The Decoder：AI News（RSS） dentro de Investigación. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理","url":"https://www.aioga.com/es/news/cmrj0wvrs04lcbilk41ofc7q5/"},"fr":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga suit cette mise à jour de The Decoder：AI News（RSS） dans la catégorie Recherche. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"Recherche","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga Actualités IA","description":"Aioga suit cette mise à jour de The Decoder：AI News（RSS） dans la catégorie Recherche. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型","url":"https://www.aioga.com/fr/news/cmrj0wvrs04lcbilk41ofc7q5/"},"de":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga KI-News","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/de/news/cmrj0wvrs04lcbilk41ofc7q5/"},"pt-BR":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga Notícias de IA","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/pt-BR/news/cmrj0wvrs04lcbilk41ofc7q5/"},"ru":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga Новости ИИ","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/ru/news/cmrj0wvrs04lcbilk41ofc7q5/"},"ar":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga أخبار الذكاء الاصطناعي","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/ar/news/cmrj0wvrs04lcbilk41ofc7q5/"},"hi":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga AI समाचार","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/hi/news/cmrj0wvrs04lcbilk41ofc7q5/"},"it":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga Notizie IA","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/it/news/cmrj0wvrs04lcbilk41ofc7q5/"},"nl":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga AI-nieuws","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/nl/news/cmrj0wvrs04lcbilk41ofc7q5/"},"tr":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga AI Haberleri","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/tr/news/cmrj0wvrs04lcbilk41ofc7q5/"},"vi":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Tin tức AI Aioga","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/vi/news/cmrj0wvrs04lcbilk41ofc7q5/"},"id":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Berita AI Aioga","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/id/news/cmrj0wvrs04lcbilk41ofc7q5/"},"th":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - ข่าว AI Aioga","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/th/news/cmrj0wvrs04lcbilk41ofc7q5/"},"pl":{"title":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型","summary":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温度和气压高度等 34 项特征，采用名为\"自适应与继承掩码\"（AIM）的自监督训练方法。在 35 项健康与行为预测任务中，SensorFM 在 34 项上超越了使用手工特征的有监督基线模型。将 SensorFM 预测结果集成到 Gemini 健康智能体后，临床医生对健康摘要的评分在上下文、个性化、可论证性、相关性和安全性五个维度均显著高于基线版本。模型参数量从约 10 万到 1 亿不等，性能随模型和数据规模同步提升。","category":"论文研究","source":"The Decoder：AI News（RSS）","pageTitle":"Google Research 推出 SensorFM：从 500 万用户万亿分钟可穿戴数据中预训练的基础模型 - Aioga Wiadomości AI","description":"Aioga tracks this update from The Decoder：AI News（RSS） under 论文研究. Google Research 推出 SensorFM，一个从 500 万 Fitbit 和 Pixel Watch 用户超过 1 万亿分钟未标注多模态传感器数据中预训练的基础模型。该模型处理光学心率、加速度、皮肤电导、皮肤温","url":"https://www.aioga.com/pl/news/cmrj0wvrs04lcbilk41ofc7q5/"}}}}