Nature Machine Intelligence最新文献

{"title":"A new perspective on the simulation of stochastic problems in fluid mechanics with diffusion models","authors":"Luca Guastoni, Ricardo Vinuesa","doi":"10.1038/s42256-025-01060-4","DOIUrl":"10.1038/s42256-025-01060-4","url":null,"abstract":"Generative deep learning models offer a fundamentally new approach for simulating stochastic processes in turbulent flows.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 6","pages":"816-817"},"PeriodicalIF":23.9,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296157","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}

{"title":"Embedding high-resolution touch across robotic hands enables adaptive human-like grasping","authors":"Zihang Zhao, Wanlin Li, Yuyang Li, Tengyu Liu, Boren Li, Meng Wang, Kai Du, Hangxin Liu, Yixin Zhu, Qining Wang, Kaspar Althoefer, Song-Chun Zhu","doi":"10.1038/s42256-025-01053-3","DOIUrl":"10.1038/s42256-025-01053-3","url":null,"abstract":"Developing robotic hands that adapt to real-world dynamics remains a fundamental challenge in robotics and machine intelligence. Despite notable advances in replicating human-hand kinematics and control algorithms, robotic systems still struggle to match human capabilities in dynamic environments, primarily due to inadequate tactile feedback. To bridge this gap, we present F-TAC Hand, a biomimetic hand featuring high-resolution tactile sensing (0.1-mm spatial resolution) across 70% of its surface area. Through optimized hand design, we overcome traditional challenges in integrating high-resolution tactile sensors while preserving the full range of motion. The hand, powered by our generative algorithm that synthesizes human-like hand configurations, demonstrates robust grasping capabilities in dynamic real-world conditions. Extensive evaluation across 600 real-world trials demonstrates that this tactile-embodied system significantly outperforms non-tactile-informed alternatives in complex manipulation tasks (P < 0.0001). These results provide empirical evidence for the critical role of rich tactile embodiment in developing advanced robotic intelligence, offering promising perspectives on the relationship between physical sensing capabilities and intelligent behaviour. Developing robotic hands that can adapt to real-world dynamics remains a substantial challenge. The authors present an AI system that mimics human-like grasping using full-hand tactile sensing and a sensory–motor feedback mechanism.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 6","pages":"889-900"},"PeriodicalIF":23.9,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01053-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144238245","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}

{"title":"Human-like object concept representations emerge naturally in multimodal large language models","authors":"Changde Du, Kaicheng Fu, Bincheng Wen, Yi Sun, Jie Peng, Wei Wei, Ying Gao, Shengpei Wang, Chuncheng Zhang, Jinpeng Li, Shuang Qiu, Le Chang, Huiguang He","doi":"10.1038/s42256-025-01049-z","DOIUrl":"10.1038/s42256-025-01049-z","url":null,"abstract":"Understanding how humans conceptualize and categorize natural objects offers critical insights into perception and cognition. With the advent of large language models (LLMs), a key question arises: can these models develop human-like object representations from linguistic and multimodal data? Here we combined behavioural and neuroimaging analyses to explore the relationship between object concept representations in LLMs and human cognition. We collected 4.7 million triplet judgements from LLMs and multimodal LLMs to derive low-dimensional embeddings that capture the similarity structure of 1,854 natural objects. The resulting 66-dimensional embeddings were stable, predictive and exhibited semantic clustering similar to human mental representations. Remarkably, the dimensions underlying these embeddings were interpretable, suggesting that LLMs and multimodal LLMs develop human-like conceptual representations of objects. Further analysis showed strong alignment between model embeddings and neural activity patterns in brain regions such as the extrastriate body area, parahippocampal place area, retrosplenial cortex and fusiform face area. This provides compelling evidence that the object representations in LLMs, although not identical to human ones, share fundamental similarities that reflect key aspects of human conceptual knowledge. Our findings advance the understanding of machine intelligence and inform the development of more human-like artificial cognitive systems. Multimodal large language models are shown to develop object concept representations similar to those of humans. These representations closely align with neural activity in brain regions involved in object recognition, revealing similarities between artificial intelligence and human cognition.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 6","pages":"860-875"},"PeriodicalIF":23.9,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144238243","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}

{"title":"Unregulated emotional risks of AI wellness apps","authors":"Julian De Freitas, I. Glenn Cohen","doi":"10.1038/s42256-025-01051-5","DOIUrl":"10.1038/s42256-025-01051-5","url":null,"abstract":"We propose that AI-driven wellness apps powered by large language models can foster extreme emotional attachments and dependencies akin to human relationships — posing risks such as ambiguous loss and dysfunctional dependence — that challenge current regulatory frameworks and necessitate safeguards and informed interventions within these platforms.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 6","pages":"813-815"},"PeriodicalIF":23.9,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144229006","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}

{"title":"A multimodal conversational agent for DNA, RNA and protein tasks","authors":"Bernardo P. de Almeida, Guillaume Richard, Hugo Dalla-Torre, Christopher Blum, Lorenz Hexemer, Priyanka Pandey, Stefan Laurent, Chandana Rajesh, Marie Lopez, Alexandre Laterre, Maren Lang, Uğur Şahin, Karim Beguir, Thomas Pierrot","doi":"10.1038/s42256-025-01047-1","DOIUrl":"10.1038/s42256-025-01047-1","url":null,"abstract":"Language models are thriving, powering conversational agents that assist and empower humans to solve a number of tasks. Recently, these models were extended to support additional modalities including vision, audio and video, demonstrating impressive capabilities across multiple domains, including healthcare. Still, conversational agents remain limited in biology as they cannot yet fully comprehend biological sequences. Meanwhile, high-performance foundation models for biological sequences have been built through self-supervision over sequencing data, but these need to be fine-tuned for each specific application, preventing generalization between tasks. In addition, these models are not conversational, which limits their utility to users with coding capabilities. Here we propose to bridge the gap between biology foundation models and conversational agents by introducing ChatNT, a multimodal conversational agent with an advanced understanding of biological sequences. ChatNT achieves new state-of-the-art results on the Nucleotide Transformer benchmark while being able to solve all tasks at once, in English, and to generalize to unseen questions. In addition, we have curated a set of more biologically relevant instruction tasks from DNA, RNA and proteins, spanning multiple species, tissues and biological processes. ChatNT reaches performance on par with state-of-the-art specialized methods on those tasks. We also present a perplexity-based technique to help calibrate the confidence of our model predictions. By applying attribution methods through the English decoder and DNA encoder, we demonstrate that ChatNT’s answers are based on biologically coherent features such as detecting the promoter TATA motif or splice site dinucleotides. Our framework for genomics instruction tuning can be extended to more tasks and data modalities (for example, structure and imaging), making it a widely applicable tool for biology. ChatNT provides a potential direction for building generally capable agents that understand biology from first principles while being accessible to users with no coding background. De Almeida, Richard and colleagues leverage transfer learning to create ChatNT, a multimodal conversational agent for DNA, RNA and protein sequences that can be instructed in natural language.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 6","pages":"928-941"},"PeriodicalIF":23.9,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01047-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144229007","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}

{"title":"Deep spectral component filtering as a foundation model for spectral analysis demonstrated in metabolic profiling","authors":"Bingsen Xue, Xinyuan Bi, Zheyi Dong, Yunzhe Xu, Minghui Liang, Xin Fang, Yizhe Yuan, Ruoxi Wang, Shuyu Liu, Rushi Jiao, Yuze Chen, Weitao Zu, Chengxiang Wang, Jianhao Zhang, Jiang Liu, Qin Zhang, Ye Yuan, Midie Xu, Ya Zhang, Yanfeng Wang, Jian Ye, Cheng Jin","doi":"10.1038/s42256-025-01027-5","DOIUrl":"10.1038/s42256-025-01027-5","url":null,"abstract":"Analysing metabolites in bioliquids through various spectroscopic methods provides valuable insights into the metabolic phenotypes. Deciphering spectral data has greatly benefited from deep-learning methods; however, data-driven solutions often struggle with data dependence on different devices, samples and spectral modalities. Most current task-specific methods have limited generalizability to different spectral analysis problems, including preprocessing, quantification and interpretation. Here, we developed a pretrained foundation model, termed deep-spectral component filtering (DSCF) through a self-supervised approach termed spectral component resolvable learning. By acquiring general spectral knowledge, DSCF achieved state-of-the-art performance for five distinct spectral analysis tasks on 11 datasets. Notably, the general pretraining led to zero-shot spectral denoising and trace-level quantification in complex mixtures. DSCF achieved molecule-level interpretation of surface-enhanced Raman spectra and mapped serum metabolic profiles from nearly 600 individuals for various diseases, including stroke, Alzheimer’s disease and prostate cancer. Overall, the proposed foundation model illustrates promising generalizability for spectral analysis and offers a clear and feasible pathway for general spectral analysis. Xue et al. develop a foundation model for spectral analysis. It excels in multiple tasks, such as denoising spectra and quantifying trace molecules, and is especially promising in identifying metabolic biomarkers of diseases such as stroke, Alzheimer’s disease and prostate cancer.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 5","pages":"743-757"},"PeriodicalIF":23.9,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144123090","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}

{"title":"Advancing molecular machine learning representations with stereoelectronics-infused molecular graphs","authors":"Daniil A. Boiko, Thiago Reschützegger, Benjamin Sanchez-Lengeling, Samuel M. Blau, Gabe Gomes","doi":"10.1038/s42256-025-01031-9","DOIUrl":"10.1038/s42256-025-01031-9","url":null,"abstract":"Molecular representation is a critical element in our understanding of the physical world and the foundation for modern molecular machine learning. Previous molecular machine learning models have used strings, fingerprints, global features and simple molecular graphs that are inherently information-sparse representations. However, as the complexity of prediction tasks increases, the molecular representation needs to encode higher fidelity information. This work introduces a new approach to infusing quantum-chemical-rich information into molecular graphs via stereoelectronic effects, enhancing expressivity and interpretability. Learning to predict the stereoelectronics-infused representation with a tailored double graph neural network workflow enables its application to any downstream molecular machine learning task without expensive quantum-chemical calculations. We show that the explicit addition of stereoelectronic information substantially improves the performance of message-passing two-dimensional machine learning models for molecular property prediction. We show that the learned representations trained on small molecules can accurately extrapolate to much larger molecular structures, yielding chemical insight into orbital interactions for previously intractable systems, such as entire proteins, opening new avenues of molecular design. Finally, we have developed a web application (simg.cheme.cmu.edu) where users can rapidly explore stereoelectronic information for their own molecular systems. Boiko et al. enhance expressiveness and interpretability of molecular representation in graph neural networks by including quantum-chemical-rich information into molecular graphs.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 5","pages":"771-781"},"PeriodicalIF":23.9,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144130227","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}

{"title":"Firefighting robots should be made responsibly","authors":"Benjamin R. van Manen, Eduard Fosch-Villaronga, Merlijn Smits","doi":"10.1038/s42256-025-01037-3","DOIUrl":"10.1038/s42256-025-01037-3","url":null,"abstract":"","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 5","pages":"676-677"},"PeriodicalIF":23.9,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144130226","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}

{"title":"Localizing AI in the global south","authors":"","doi":"10.1038/s42256-025-01057-z","DOIUrl":"10.1038/s42256-025-01057-z","url":null,"abstract":"Countries in the global south stand to benefit considerably from AI developments and are taking the lead in determining the direction of inclusive AI research efforts.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 5","pages":"675-675"},"PeriodicalIF":23.9,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01057-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144113872","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}

{"title":"A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics","authors":"Mengyun Qiao, Kathryn A. McGurk, Shuo Wang, Paul M. Matthews, Declan P. O’Regan, Wenjia Bai","doi":"10.1038/s42256-025-01035-5","DOIUrl":"10.1038/s42256-025-01035-5","url":null,"abstract":"Understanding the structure and motion of the heart is crucial for diagnosing and managing cardiovascular diseases, the leading cause of global death. There is wide variation in cardiac shape and motion patterns, influenced by demographic, anthropometric and disease factors. Unravelling normal patterns of shape and motion, and understanding how each individual deviates from the norm, would facilitate accurate diagnosis and personalized treatment strategies. Here, to this end, we developed a conditional generative model, MeshHeart, to learn the distribution of shape and motion patterns for the left and right ventricles of the heart. To model the high-dimensional spatio-temporal mesh data, MeshHeart uses a geometric encoder to represent cardiac meshes in a latent space and a temporal transformer to model the motion dynamics of latent representations. Based on MeshHeart, we investigate the latent space of 3D + t cardiac mesh sequences and propose a distance metric, latent delta, which quantifies the deviation of a real heart from its personalized normative pattern. Here, 3D + t refers to three-dimensional data evolving over time. In experiments using a large cardiac magnetic resonance image dataset of 38,309 participants from the UK Biobank, MeshHeart demonstrates high performance in cardiac mesh sequence reconstruction and generation. Latent space features are discriminative for cardiac disease classification, whereas latent delta exhibits strong correlations with clinical phenotypes in phenome-wide association studies. MeshHeart, a conditional generative model for time-resolved 3D heart mesh generation, is proposed by Qiao et al. to unravel heart motion patterns. Their findings could advance diagnosis and treatment strategies for cardiovascular diseases.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 5","pages":"800-811"},"PeriodicalIF":23.9,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01035-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144088333","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}