Pub Date : 2025-10-13DOI: 10.1038/s42256-025-01132-5
Deeksha Arya, Hiroya Maeda, Yoshihide Sekimoto
The organizers reflect on how a multi-year, multi-country benchmark aligned AI research in road damage detection with practical and regional constraints, steering it towards deployment relevance.
{"title":"Insights from the Road Damage Detection Challenge Series (2018–2024)","authors":"Deeksha Arya, Hiroya Maeda, Yoshihide Sekimoto","doi":"10.1038/s42256-025-01132-5","DOIUrl":"10.1038/s42256-025-01132-5","url":null,"abstract":"The organizers reflect on how a multi-year, multi-country benchmark aligned AI research in road damage detection with practical and regional constraints, steering it towards deployment relevance.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 10","pages":"1768-1769"},"PeriodicalIF":23.9,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145352977","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}
Pub Date : 2025-10-13DOI: 10.1038/s42256-025-01123-6
Jovana Davidovic
Most policy proposals aimed at managing the risks of artificial intelligence (AI)-enabled weapons rely heavily on meaningful human control or appropriate human judgment for risk mitigation. This Comment argues that there are various ways humans can exert such control over AI, and that developing a careful taxonomy of these is necessary for building actionable risk-mitigation policies for warfighting AI.
{"title":"Rethinking human roles in AI warfare","authors":"Jovana Davidovic","doi":"10.1038/s42256-025-01123-6","DOIUrl":"10.1038/s42256-025-01123-6","url":null,"abstract":"Most policy proposals aimed at managing the risks of artificial intelligence (AI)-enabled weapons rely heavily on meaningful human control or appropriate human judgment for risk mitigation. This Comment argues that there are various ways humans can exert such control over AI, and that developing a careful taxonomy of these is necessary for building actionable risk-mitigation policies for warfighting AI.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 10","pages":"1593-1595"},"PeriodicalIF":23.9,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145352969","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}
Humanization is a critical process in designing antibodies and nanobodies for clinical trials. Developing widely recognized deep learning frameworks for this task remains valuable yet challenging. Here, inspired by the success of diffusion models, we introduce HuDiff, an adaptive diffusion approach for humanizing antibodies and nanobodies from scratch, referred to as HuDiff-Ab and HuDiff-Nb. This approach initiates humanization exclusively with complementarity-determining region sequences, eliminating the need for humanized templates. On public benchmarks, HuDiff-Ab generates humanized antibodies that more closely resemble experimentally humanized sequences than existing models. Similarly, HuDiff-Nb produces nanobodies with higher humanness scores and nativeness than alternative methods. We apply HuDiff to humanize a murine antibody targeting the SARS-CoV-2 receptor-binding domain and two alpaca-derived nanobodies, one targeting the receptor-binding domain and the other targeting the C345c domain of C3. Bio-layer interferometry shows the best-performing humanized antibody retains binding affinity comparable to the parental antibody (0.15 nM versus 0.12 nM). Both humanized nanobodies maintain binding to their respective antigens, with the best-performing one exhibiting a substantially enhanced affinity (2.52 nM versus 5.47 nM), corresponding to a 54% improvement over the parental nanobody. Neutralization assays confirm that the humanized sequences effectively neutralize the virus. These results demonstrate that HuDiff improves antibody and nanobody humanness while preserving or enhancing binding and function. Jian Ma et al. present HuDiff, a diffusion-based deep learning framework that humanizes antibodies and nanobodies (a small type of antibody) without templates. The model achieves improved humanness while preserving or enhancing binding strength, and the authors show promising results in virus neutralization experiments.
{"title":"An adaptive autoregressive diffusion approach to design active humanized antibodies and nanobodies","authors":"Jian Ma, Fandi Wu, Tingyang Xu, Shaoyong Xu, Wei Liu, Liang Yan, Minghao Qu, Xiaoke Yang, Qifeng Bai, Junyu Xiao, Jianhua Yao","doi":"10.1038/s42256-025-01120-9","DOIUrl":"10.1038/s42256-025-01120-9","url":null,"abstract":"Humanization is a critical process in designing antibodies and nanobodies for clinical trials. Developing widely recognized deep learning frameworks for this task remains valuable yet challenging. Here, inspired by the success of diffusion models, we introduce HuDiff, an adaptive diffusion approach for humanizing antibodies and nanobodies from scratch, referred to as HuDiff-Ab and HuDiff-Nb. This approach initiates humanization exclusively with complementarity-determining region sequences, eliminating the need for humanized templates. On public benchmarks, HuDiff-Ab generates humanized antibodies that more closely resemble experimentally humanized sequences than existing models. Similarly, HuDiff-Nb produces nanobodies with higher humanness scores and nativeness than alternative methods. We apply HuDiff to humanize a murine antibody targeting the SARS-CoV-2 receptor-binding domain and two alpaca-derived nanobodies, one targeting the receptor-binding domain and the other targeting the C345c domain of C3. Bio-layer interferometry shows the best-performing humanized antibody retains binding affinity comparable to the parental antibody (0.15 nM versus 0.12 nM). Both humanized nanobodies maintain binding to their respective antigens, with the best-performing one exhibiting a substantially enhanced affinity (2.52 nM versus 5.47 nM), corresponding to a 54% improvement over the parental nanobody. Neutralization assays confirm that the humanized sequences effectively neutralize the virus. These results demonstrate that HuDiff improves antibody and nanobody humanness while preserving or enhancing binding and function. Jian Ma et al. present HuDiff, a diffusion-based deep learning framework that humanizes antibodies and nanobodies (a small type of antibody) without templates. The model achieves improved humanness while preserving or enhancing binding strength, and the authors show promising results in virus neutralization experiments.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 10","pages":"1698-1712"},"PeriodicalIF":23.9,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145352973","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}
Pub Date : 2025-09-29DOI: 10.1038/s42256-025-01118-3
Yuchi Qiu
Designing and optimizing proteins by mutagenesis suffers from the overwhelming space of possible variants. A recent study developed µProtein, a reinforcement learning model coupled with a protein language model as a surrogate oracle, to accelerate this process towards high-functioning proteins.
{"title":"An integrated framework to accelerate protein design through mutagenesis","authors":"Yuchi Qiu","doi":"10.1038/s42256-025-01118-3","DOIUrl":"10.1038/s42256-025-01118-3","url":null,"abstract":"Designing and optimizing proteins by mutagenesis suffers from the overwhelming space of possible variants. A recent study developed µProtein, a reinforcement learning model coupled with a protein language model as a surrogate oracle, to accelerate this process towards high-functioning proteins.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 10","pages":"1596-1597"},"PeriodicalIF":23.9,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145352989","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}
Pub Date : 2025-09-24DOI: 10.1038/s42256-025-01100-z
Michael Jendrusch, Jan O. Korbel
Proteins play diverse roles in all domains of life and are extensively harnessed as biomolecules in biotechnology, with applications spanning from fundamental research to biomedicine. Therefore, there is considerable interest in computationally designing proteins with specified properties. Protein structure generative models provide a means to design protein structures in a controllable manner and have been successfully applied to address various protein design tasks. Such models are paired with protein sequence and structure predictors to produce and select protein sequences for experimental testing. However, current protein structure generators face important limitations for proteins with more than 400 amino acids and require retraining for protein design tasks unseen during model training. To address the first issue, we introduce salad, a family of sparse all-atom denoising models for protein structure generation. Our models are smaller and faster than the state of the art and matching or improving design quality, successfully generating structures for protein lengths up to 1,000 amino acids. To address the second issue, we combine salad with structure editing, a sampling strategy for expanding the capability of protein denoising models to unseen tasks. We apply our approach to a variety of challenging protein design tasks, from generating protein scaffolds containing functional protein motifs (motif scaffolding) to designing proteins capable of adopting multiple distinct folds under different conditions (multi-state protein design), demonstrating the flexibility of salad and structure editing. A small and fast diffusion model is presented, which is able to efficiently generate long protein backbones.
{"title":"Efficient protein structure generation with sparse denoising models","authors":"Michael Jendrusch, Jan O. Korbel","doi":"10.1038/s42256-025-01100-z","DOIUrl":"10.1038/s42256-025-01100-z","url":null,"abstract":"Proteins play diverse roles in all domains of life and are extensively harnessed as biomolecules in biotechnology, with applications spanning from fundamental research to biomedicine. Therefore, there is considerable interest in computationally designing proteins with specified properties. Protein structure generative models provide a means to design protein structures in a controllable manner and have been successfully applied to address various protein design tasks. Such models are paired with protein sequence and structure predictors to produce and select protein sequences for experimental testing. However, current protein structure generators face important limitations for proteins with more than 400 amino acids and require retraining for protein design tasks unseen during model training. To address the first issue, we introduce salad, a family of sparse all-atom denoising models for protein structure generation. Our models are smaller and faster than the state of the art and matching or improving design quality, successfully generating structures for protein lengths up to 1,000 amino acids. To address the second issue, we combine salad with structure editing, a sampling strategy for expanding the capability of protein denoising models to unseen tasks. We apply our approach to a variety of challenging protein design tasks, from generating protein scaffolds containing functional protein motifs (motif scaffolding) to designing proteins capable of adopting multiple distinct folds under different conditions (multi-state protein design), demonstrating the flexibility of salad and structure editing. A small and fast diffusion model is presented, which is able to efficiently generate long protein backbones.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 9","pages":"1429-1445"},"PeriodicalIF":23.9,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01100-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145129501","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}
Pub Date : 2025-09-22DOI: 10.1038/s42256-025-01105-8
Roberto Ferroni, Gaetano D’Avola, Giorgia Sciarrone, Gabriele Righi, Claudia De Santis, Jacopo Carpaneto, Marta Gandolla, Giulio Del Popolo, Silvestro Micera, Tommaso Proietti
Spinal cord injury (SCI) disrupts neuromuscular control, severely affecting independence and quality of life. Although upper limb wearable robots hold considerable promise for functional restoration, most existing prototypes have been validated minimally in people with SCI and target almost exclusively hand opening and closing. We introduce a lightweight, modular assistive soft exosuit that simultaneously and automatically supports shoulder abduction and elbow flexion or extension movements using lightweight fabric-based pneumatic actuators, controlled through inertial sensors. The individual elbow modules were first validated in 11 healthy volunteers, and subsequently tested, together with the shoulder module, in 15 individuals with cervical SCI (C4–C7, AIS A–D). In the SCI participants, exosuits assistance resulted in increased static endurance time (by more than 250%), and lower activity of the primary muscles involved in dynamic tasks (by up to 50%). The two SCI participants retaining prehensile capability also improved their scores in the box and block test when assisted. Moreover, the soft actuation provided a safe, comfortable and easy-to-use solution that was positively appreciated by the participants. Collectively, these results provide encouraging evidence that exosuits can augment upper limb motor performance, and may ultimately translate into greater functional independence and quality of life for the SCI population. A lightweight, modular assistive soft exosuit is introduced, which supports shoulder and elbow movement in individuals with cervical spinal cord injury. The device enhances endurance and range of motion, reduces muscle effort and improves clinical test scores.
{"title":"A multi-joint soft exosuit improves shoulder and elbow motor functions in individuals with spinal cord injury","authors":"Roberto Ferroni, Gaetano D’Avola, Giorgia Sciarrone, Gabriele Righi, Claudia De Santis, Jacopo Carpaneto, Marta Gandolla, Giulio Del Popolo, Silvestro Micera, Tommaso Proietti","doi":"10.1038/s42256-025-01105-8","DOIUrl":"10.1038/s42256-025-01105-8","url":null,"abstract":"Spinal cord injury (SCI) disrupts neuromuscular control, severely affecting independence and quality of life. Although upper limb wearable robots hold considerable promise for functional restoration, most existing prototypes have been validated minimally in people with SCI and target almost exclusively hand opening and closing. We introduce a lightweight, modular assistive soft exosuit that simultaneously and automatically supports shoulder abduction and elbow flexion or extension movements using lightweight fabric-based pneumatic actuators, controlled through inertial sensors. The individual elbow modules were first validated in 11 healthy volunteers, and subsequently tested, together with the shoulder module, in 15 individuals with cervical SCI (C4–C7, AIS A–D). In the SCI participants, exosuits assistance resulted in increased static endurance time (by more than 250%), and lower activity of the primary muscles involved in dynamic tasks (by up to 50%). The two SCI participants retaining prehensile capability also improved their scores in the box and block test when assisted. Moreover, the soft actuation provided a safe, comfortable and easy-to-use solution that was positively appreciated by the participants. Collectively, these results provide encouraging evidence that exosuits can augment upper limb motor performance, and may ultimately translate into greater functional independence and quality of life for the SCI population. A lightweight, modular assistive soft exosuit is introduced, which supports shoulder and elbow movement in individuals with cervical spinal cord injury. The device enhances endurance and range of motion, reduces muscle effort and improves clinical test scores.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 9","pages":"1390-1402"},"PeriodicalIF":23.9,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145129497","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}
Pub Date : 2025-09-22DOI: 10.1038/s42256-025-01086-8
Winston Chen, Yifan Jiang, William Stafford Noble, Yang Young Lu
Machine learning (ML) models are powerful tools for detecting complex patterns, yet their ‘black-box’ nature limits their interpretability, hindering their use in critical domains like healthcare and finance. Interpretable ML methods aim to explain how features influence model predictions but often focus on univariate feature importance, overlooking complex feature interactions. Although recent efforts extend interpretability to feature interactions, existing approaches struggle with robustness and error control, especially under data perturbations. In this study, we introduce Diamond, a method for trustworthy feature interaction discovery. Diamond uniquely integrates the model-X knockoffs framework to control the false discovery rate, ensuring a low proportion of falsely detected interactions. Diamond includes a non-additivity distillation procedure that refines existing interaction importance measures to isolate non-additive interaction effects and preserve false discovery rate control. This approach addresses the limitations of off-the-shelf interaction measures, which, when used naively, can lead to inaccurate discoveries. Diamond’s applicability spans a broad class of ML models, including deep neural networks, transformers, tree-based models and factorization-based models. Empirical evaluations on both simulated and real datasets across various biomedical studies demonstrate its utility in enabling reliable data-driven scientific discoveries. Diamond represents a significant step forward in leveraging ML for scientific innovation and hypothesis generation. Diamond, a statistically rigorous method, is capable of finding meaningful feature interactions within machine learning models, making black-box models more interpretable for science and medicine.
{"title":"Error-controlled non-additive interaction discovery in machine learning models","authors":"Winston Chen, Yifan Jiang, William Stafford Noble, Yang Young Lu","doi":"10.1038/s42256-025-01086-8","DOIUrl":"10.1038/s42256-025-01086-8","url":null,"abstract":"Machine learning (ML) models are powerful tools for detecting complex patterns, yet their ‘black-box’ nature limits their interpretability, hindering their use in critical domains like healthcare and finance. Interpretable ML methods aim to explain how features influence model predictions but often focus on univariate feature importance, overlooking complex feature interactions. Although recent efforts extend interpretability to feature interactions, existing approaches struggle with robustness and error control, especially under data perturbations. In this study, we introduce Diamond, a method for trustworthy feature interaction discovery. Diamond uniquely integrates the model-X knockoffs framework to control the false discovery rate, ensuring a low proportion of falsely detected interactions. Diamond includes a non-additivity distillation procedure that refines existing interaction importance measures to isolate non-additive interaction effects and preserve false discovery rate control. This approach addresses the limitations of off-the-shelf interaction measures, which, when used naively, can lead to inaccurate discoveries. Diamond’s applicability spans a broad class of ML models, including deep neural networks, transformers, tree-based models and factorization-based models. Empirical evaluations on both simulated and real datasets across various biomedical studies demonstrate its utility in enabling reliable data-driven scientific discoveries. Diamond represents a significant step forward in leveraging ML for scientific innovation and hypothesis generation. Diamond, a statistically rigorous method, is capable of finding meaningful feature interactions within machine learning models, making black-box models more interpretable for science and medicine.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 9","pages":"1541-1554"},"PeriodicalIF":23.9,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01086-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145129499","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}
Pub Date : 2025-09-18DOI: 10.1038/s42256-025-01104-9
Fotios Drakopoulos, Lloyd Pellatt, Shievanie Sabesan, Yiqing Xia, Andreas Fragner, Nicholas A. Lesica
Computational models of auditory processing can be valuable tools for research and technology development. Models of the cochlea are highly accurate and widely used, but models of the auditory brain lag far behind in both performance and penetration. Here we present ICNet, a convolutional encoder–decoder model of neural coding in the inferior colliculus. We developed ICNet using large-scale intracranial recordings from anaesthetized gerbils, addressing three key modelling challenges that are common across all sensory systems: capturing the full statistical structure of neuronal response patterns; accounting for physiological and experimental non-stationarity; and extracting features of sensory processing that are shared across different brains. ICNet provides highly accurate simulation of multi-unit neural responses to a wide range of complex sounds, including near-perfect responses to speech. It also reproduces key neurophysiological phenomena such as forward masking and dynamic range adaptation. ICNet can be used to simulate activity from thousands of neural units or to provide a compact representation of early central auditory processing through its latent dynamics, facilitating a wide range of hearing and audio applications. It can also serve as a foundation core, providing a baseline neural representation for models of active listening or higher-level auditory processing. Drakopoulos et al. present a model that captures the transformation from sound waves to neural activity patterns underlying early auditory processing. The model reproduces neural responses to a range of complex sounds and key neurophysiological phenomena.
{"title":"Modelling neural coding in the auditory midbrain with high resolution and accuracy","authors":"Fotios Drakopoulos, Lloyd Pellatt, Shievanie Sabesan, Yiqing Xia, Andreas Fragner, Nicholas A. Lesica","doi":"10.1038/s42256-025-01104-9","DOIUrl":"10.1038/s42256-025-01104-9","url":null,"abstract":"Computational models of auditory processing can be valuable tools for research and technology development. Models of the cochlea are highly accurate and widely used, but models of the auditory brain lag far behind in both performance and penetration. Here we present ICNet, a convolutional encoder–decoder model of neural coding in the inferior colliculus. We developed ICNet using large-scale intracranial recordings from anaesthetized gerbils, addressing three key modelling challenges that are common across all sensory systems: capturing the full statistical structure of neuronal response patterns; accounting for physiological and experimental non-stationarity; and extracting features of sensory processing that are shared across different brains. ICNet provides highly accurate simulation of multi-unit neural responses to a wide range of complex sounds, including near-perfect responses to speech. It also reproduces key neurophysiological phenomena such as forward masking and dynamic range adaptation. ICNet can be used to simulate activity from thousands of neural units or to provide a compact representation of early central auditory processing through its latent dynamics, facilitating a wide range of hearing and audio applications. It can also serve as a foundation core, providing a baseline neural representation for models of active listening or higher-level auditory processing. Drakopoulos et al. present a model that captures the transformation from sound waves to neural activity patterns underlying early auditory processing. The model reproduces neural responses to a range of complex sounds and key neurophysiological phenomena.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 9","pages":"1478-1493"},"PeriodicalIF":23.9,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01104-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145129516","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}
Pub Date : 2025-09-17DOI: 10.1038/s42256-025-01128-1
Yuepeng Jiang, Pingping Zhang, Miaozhe Huo, Shuai Cheng Li
{"title":"Author Correction: Deep learning-based prediction of the selection factors for quantifying selection in immune receptor repertoires","authors":"Yuepeng Jiang, Pingping Zhang, Miaozhe Huo, Shuai Cheng Li","doi":"10.1038/s42256-025-01128-1","DOIUrl":"10.1038/s42256-025-01128-1","url":null,"abstract":"","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 9","pages":"1587-1587"},"PeriodicalIF":23.9,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01128-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145129498","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：