Nature Machine Intelligence最新文献_第4页

Transfer learning with deployment-covariate recalibration for survival prediction under covariate shift 协变量移位下部署-协变量再校准的生存预测迁移学习

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-18 DOI: 10.1038/s42256-026-01285-x

Lulu Pan, Genming Zhao, Yongfu Yu, Guoyou Qin

{"title":"Transfer learning with deployment-covariate recalibration for survival prediction under covariate shift","authors":"Lulu Pan, Genming Zhao, Yongfu Yu, Guoyou Qin","doi":"10.1038/s42256-026-01285-x","DOIUrl":"10.1038/s42256-026-01285-x","url":null,"abstract":"Clinical prediction models often underperform in deployment populations that differ from historical training cohorts because of covariate shifts, but outcome-based updating is infeasible when deployment outcomes are unavailable. This challenge is further amplified when the target training cohort has limited samples or sparse events. Here we propose CoxRTL, a transfer learning framework with deployment-covariate recalibration for survival prediction under covariate shift. CoxRTL borrows information from external cohorts to improve estimation, uses transferability screening and debiasing to mitigate external effect heterogeneity, and embeds density-ratio weighting into transfer estimation, yielding a distribution-adaptive weighted partial likelihood that aligns historical training cohorts with the deployment-covariate distribution. We evaluated CoxRTL in simulations and two cohorts. Simulations showed improved prediction under training–deployment covariate shift. Using early National Health and Nutrition Examination Survey data, we developed prognostic models for 20 chronic diseases in older adults and evaluated their performance in later survey cohorts. CoxRTL achieved higher discrimination than models trained only in older adults (median C-index improvement, 0.056; range, 0.016–0.126) or in the full population (0.042; 0.013–0.107). It also improved calibration, clinical utility and risk stratification, while identifying variables with greater predictive contribution across diseases. Independent replication in the Shanghai Suburban Adult Cohort and Biobank confirmed robustness under geographic and temporal shifts. These findings support CoxRTL as a feasible strategy for developing prediction models for prespecified deployment populations when target training data are limited. Pan et al. present CoxRTL, a recalibrated transfer learning strategy that leverages external cohorts to improve survival prediction under covariate shift when target training data are limited and deployment outcomes are unavailable.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 8","pages":"1312-1326"},"PeriodicalIF":29.8,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Agentic AI and cybersecurity, the story so far 代理人工智能和网络安全，目前为止的故事

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-18 DOI: 10.1038/s42256-026-01301-0

引用次数: 0

Machine learning of artistic fingerprints in jazz 爵士乐艺术指纹的机器学习

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-17 DOI: 10.1038/s42256-026-01279-9

Huw Cheston, Reuben Bance, Peter M. C. Harrison

{"title":"Machine learning of artistic fingerprints in jazz","authors":"Huw Cheston, Reuben Bance, Peter M. C. Harrison","doi":"10.1038/s42256-026-01279-9","DOIUrl":"10.1038/s42256-026-01279-9","url":null,"abstract":"Artists are often recognizable through collections of distinctive patterns (‘fingerprints’) in their work. Identifying such traits has important applications in authorship attribution, education, cultural heritage research and historical analysis. Here we focus on music, a domain with a rich tradition of theoretical and mathematical analysis. We train a variety of supervised learning models to identify 20 iconic jazz musicians from a curated dataset of 84 h of recordings. In particular, we introduce a multi-input architecture that represents four musical domains separately: melody, harmony, rhythm and dynamics. This design allows us to accurately identify individual performers (our best model obtains 94% accuracy across 20 classes) and to examine which musical elements most strongly distinguish between individual artists. We release open-source implementations of our models and an accompanying web application for exploring our results. Cheston et al. develop a machine learning pipeline that identifies 20 iconic jazz pianists from audio recordings with up to 94% accuracy, revealing how melody, harmony, rhythm and dynamics shape each performer’s individual musical fingerprint.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 8","pages":"1261-1274"},"PeriodicalIF":29.8,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-026-01279-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148769339","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards general auditory intelligence for machine listening and speaking 面向机器听和说的通用听觉智能

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-14 DOI: 10.1038/s42256-026-01281-1

Siyin Wang, Zengrui Jin, Changli Tang, Qiujia Li, Bo Li, Chen Chen, Yuchen Hu, Wenyi Yu, Yixuan Li, Jimin Zhuang, Yudong Yang, Mingqiu Wang, Michael Han, Yifan Ding, Junwen Bai, Tom Ouyang, Shuo-yiin Chang, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Lu Lu, Guangzhi Sun, Zhehuai Chen, Ji Wu, Bowen Zhou, Yuxuan Wang, Tara Sainath, Yonghui Wu, Chao Zhang

{"title":"Towards general auditory intelligence for machine listening and speaking","authors":"Siyin Wang, Zengrui Jin, Changli Tang, Qiujia Li, Bo Li, Chen Chen, Yuchen Hu, Wenyi Yu, Yixuan Li, Jimin Zhuang, Yudong Yang, Mingqiu Wang, Michael Han, Yifan Ding, Junwen Bai, Tom Ouyang, Shuo-yiin Chang, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Lu Lu, Guangzhi Sun, Zhehuai Chen, Ji Wu, Bowen Zhou, Yuxuan Wang, Tara Sainath, Yonghui Wu, Chao Zhang","doi":"10.1038/s42256-026-01281-1","DOIUrl":"10.1038/s42256-026-01281-1","url":null,"abstract":"Computer audition aims to enable machines to understand, process and generate human-audible signals, including speech, environmental sound and music. The field is now evolving beyond traditional paradigms to fully leverage the capabilities of foundation models, towards more comprehensive understanding, more natural generation and more human-like interaction. Audio, as a modality rich in semantic, emotional and contextual cues, has a vital role in achieving naturalistic and embodied machine intelligence. This Review provides a comprehensive review of recent progress in integrating audio into large language models, with a focus on four key areas: audio comprehension, audio generation, speech-based interaction and audio–visual understanding. We analyse how large language models are reshaping audio perception and reasoning, enabling systems to understand sound at a deeper semantic level, generate expressive audio outputs and engage in human-like spoken interaction. Furthermore, we explore how the fusion of audio and visual modalities enhances situational awareness and cross-modal reasoning, pushing the boundaries of multimodal intelligence. This Review not only synthesizes existing research but also identifies critical challenges and future directions for building general auditory intelligence capable of perceiving, understanding and interacting through sound as naturally as humans do. Wang et al. summarize advances in machine listening and speaking, speech-based interaction, and audio–visual understanding.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 8","pages":"1201-1220"},"PeriodicalIF":29.8,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148785263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards principled knowledge editing methods for large language model reasoning 面向大型语言模型推理的原则性知识编辑方法研究

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-14 DOI: 10.1038/s42256-026-01276-y

Ningyu Zhang, Yunzhi Yao, Jiaxin Qin, Haoming Xu, Yuqi Zhu, Zeping Yu, Mengru Wang, Yuqi Tang, Jia-Chen Gu, Shumin Deng, Huajun Chen

{"title":"Towards principled knowledge editing methods for large language model reasoning","authors":"Ningyu Zhang, Yunzhi Yao, Jiaxin Qin, Haoming Xu, Yuqi Zhu, Zeping Yu, Mengru Wang, Yuqi Tang, Jia-Chen Gu, Shumin Deng, Huajun Chen","doi":"10.1038/s42256-026-01276-y","DOIUrl":"10.1038/s42256-026-01276-y","url":null,"abstract":"Knowledge editing has emerged as a promising approach that leverages understanding of a model’s inner knowledge mechanisms to enable precise knowledge updates and behaviour control without costly retraining. It is particularly appealing for enabling continuous knowledge adaptation, a capability essential for building truly intelligent, self-evolving AI systems. However, current methods treat large language models as modular knowledge stores where facts can be edited independently, ignoring the fact that knowledge forms an interconnected system in which elements depend on each other. As large language models increasingly exhibit sophisticated reasoning abilities, such as spanning multistep deduction and causal inference, the need for reasoning-consistent knowledge updates becomes critical. In this Perspective we explore some limitations of existing knowledge editing techniques and argue that effective knowledge editing must account for the intricate nature of knowledge representation. We outline three promising research directions: (1) addressing knowledge interdependence through deductive closure circuit editing; (2) integrating model beliefs and confidence into the editing process; and (3) enabling contextualized updates for complex, interdependent knowledge forms. Together, these directions suggest a pathway towards more principled knowledge editing methods capable of supporting the next generation of adaptive, reasoning-driven AI systems. Chen et al. explore limitations of current knowledge editing techniques in large language models and propose three promising research directions that respect the complexity of knowledge representation in a real-world setting.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 8","pages":"1189-1200"},"PeriodicalIF":29.8,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148785258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning contact representations in real-world clutter for universal robotic grasping 学习现实世界杂波中的接触表示用于通用机器人抓取

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-12 DOI: 10.1038/s42256-026-01292-y

Xianli Wang, Lap Mou Tam, Qingsong Xu

{"title":"Learning contact representations in real-world clutter for universal robotic grasping","authors":"Xianli Wang, Lap Mou Tam, Qingsong Xu","doi":"10.1038/s42256-026-01292-y","DOIUrl":"10.1038/s42256-026-01292-y","url":null,"abstract":"A long-standing goal in robotics is to create general-purpose agents that can learn foundational skills applicable across diverse hardware and environments. In manipulation, this is hindered by a fundamental mismatch: deep learning policies are data-efficient but hardware-specific, whereas analytical planners are hardware-agnostic but fail under perceptual uncertainty. Here we introduce SpaHybGen, a framework that unifies their strengths through learned, universal contact representations. We first train a neural network to infer spatial contact features—a hardware-agnostic representation of potential grasp points—directly from noisy depth observations. These features then guide a differentiable optimizer that computes stable grasps for articulated hand models. This hybrid design enables zero-shot generalization: our system, trained once, successfully empowered seven distinct robotic hands (from two to five fingers) without any hardware-specific retraining, achieving grasping success rates of 94.3%–98.0% in semi-cluttered scenes. It further enabled dynamic grasping at 20 Hz in dense clutter and multi-hand coordination for complex tasks. By decoupling perception from action through a shared contact interface, we provide a pathway towards reusable and adaptable manipulation intelligence, a key step for general-purpose robotics. Our code and models are open-sourced to support this vision. Wang et al. design efficient robot–environment interaction representations that achieve generalization across articulated robotic hand models and task adaptability in diverse cluttered grasping scenarios, suggesting a path towards general-purpose robotics.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 9","pages":"1396-1410"},"PeriodicalIF":29.8,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Impact-resistant, autonomous robots inspired by tensegrity architecture 受张拉整体结构启发的抗冲击自主机器人

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-10 DOI: 10.1038/s42256-026-01280-2

William R. Johnson III, Xiaonan Huang, Shiyang Lu, Kun Wang, Luca Cimatti, Marco Carati, Joran W. Booth, Kostas E. Bekris, Rebecca Kramer-Bottiglio

{"title":"Impact-resistant, autonomous robots inspired by tensegrity architecture","authors":"William R. Johnson III, Xiaonan Huang, Shiyang Lu, Kun Wang, Luca Cimatti, Marco Carati, Joran W. Booth, Kostas E. Bekris, Rebecca Kramer-Bottiglio","doi":"10.1038/s42256-026-01280-2","DOIUrl":"10.1038/s42256-026-01280-2","url":null,"abstract":"Tensegrity robots—composed of rigid struts suspended in a network of elastic cables—have been proposed as the next generation of planetary rovers and disaster response platforms, with their inherent impact resilience potentially eliminating the need for separate landers if they can survive aerial deployment. Although non-robotic tensegrity structures have demonstrated substantial impact resistance, integrating this property into autonomous robotic systems remains a grand challenge. Here we present Tribar, a three-bar tensegrity robot capable of surviving high-impact landings (at least 5.7 m) and autonomously navigating unstructured terrain post impact. We characterize the robot’s locomotion, evaluate its autonomous navigation capabilities, benchmark its performance relative to state-of-the-art tensegrity robots and demonstrate its robustness through successful locomotion after a cliff fall. Johnson et al. demonstrate an autonomous three-bar tensegrity robot capable of robust locomotion across varied terrains even after extreme impacts, including a 5.7-m drop onto asphalt.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 8","pages":"1290-1301"},"PeriodicalIF":29.8,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148728938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Trajectory forecasting lifts the femtosecond ceiling in molecular simulation 轨迹预测提升了分子模拟的飞秒上限

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-05 DOI: 10.1038/s42256-026-01275-z

Seyed Mohamad Moosavi

引用次数: 0

Reinforcement learning steers generative crystal design 强化学习指导生成晶体设计

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-03 DOI: 10.1038/s42256-026-01282-0

Zhendong Cao, Lei Wang

引用次数: 0

Beyond representational alignment with brain-guided language models for robust reasoning 超越表征对齐与大脑引导的语言模型稳健推理

IF 29.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2026-08-03 DOI: 10.1038/s42256-026-01278-w

Mingqing Xiao (, ), Kai Du (, ), Zhouchen Lin (, )

{"title":"Beyond representational alignment with brain-guided language models for robust reasoning","authors":"Mingqing Xiao \u0000 (, ), Kai Du \u0000 (, ), Zhouchen Lin \u0000 (, )","doi":"10.1038/s42256-026-01278-w","DOIUrl":"10.1038/s42256-026-01278-w","url":null,"abstract":"The correspondence between large language models (LLMs) and the neural mechanisms underlying human higher-order cognition remains insufficiently characterized. Given that language and reasoning in the human brain appear dissociable, an open question is whether LLMs align with neural signals from reasoning-related regions and whether such signals can improve them. Here, focusing on deductive reasoning, we show that LLM internal representations are not only partially aligned with task-based functional magnetic resonance imaging activity but can also be directly enhanced by these signals. Using a neural predictivity metric, we find that LLMs explain a substantial fraction of the explainable variance in reasoning-related regions at the aggregate level, whereas predictivity within specific reasoning types is lower, indicating both alignment and divergence. Building on this, we propose a brain-guided framework: we steer model representations along directions induced by the joint structure of model and brain representations, applying intervention at inference and fine tuning during training. We demonstrate that task-evoked brain signals can directly enhance LLM reasoning, yielding gains orthogonal to language-only supervision across ten LLMs (1.5B–72B parameters), with transfer across reasoning types and up to 13% absolute accuracy gain. Our results advance LLM–brain correspondences from correlation to guidance, establishing a brain-signal-driven pathway towards more robust and cognitively aligned artificial intelligence. Xiao et al. show that large language models partially align with human brain activity during deductive reasoning. They further show that brain signals can directly guide and improve model performance, with transfer across reasoning types.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 8","pages":"1275-1289"},"PeriodicalIF":29.8,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148693540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0