Mahmud Hasan Saikot, Sydney Spiegel, Sudheera Akalanka Kariyawasam, Andrew Stefka, Josh Chrisler, Jianguo Zhao
{"title":"Tensegrity continuum robots enable task-adaptive morphologies for cooperative behaviours","authors":"Mahmud Hasan Saikot, Sydney Spiegel, Sudheera Akalanka Kariyawasam, Andrew Stefka, Josh Chrisler, Jianguo Zhao","doi":"10.1038/s42256-026-01335-4","DOIUrl":"https://doi.org/10.1038/s42256-026-01335-4","url":null,"abstract":"Robots that can change their morphologies and behaviours for different tasks and environments hold great promise for adaptable, multifunctional systems. Modular reconfigurable robots can achieve such functionalities by docking and rearranging individual units, but most rely on rigid modules that lack structural compliance, resulting in limited capabilities. Continuum robots offer compliance through flexible backbones, yet they cannot self-reconfigure into task-adaptive multi-robot configurations. Here we introduce a modular reconfigurable robot that unifies the advantages of both architectures by combining a tensegrity-based compliant body with claw-based connection mechanisms. Each robot can manipulate and locomote independently, and multiple robots can self-reconfigure into different morphologies (for example, chains, loops, branches) for cooperative manipulation and locomotion. We demonstrate the robots’ capability across diverse tasks and environments, including coordinated object manipulation and transport, multimodal locomotion, and loco-manipulation in real-world scenarios. These results lay a foundation for adaptable and multifunctional robotic collectives, with broad potential applications in manufacturing, space exploration and search-and-rescue operations.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"91 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2026-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149397154","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}
Till Richter, Eric Zimmermann, James Hall, Fabian J. Theis, Srivatsan Raghavan, Peter S. Winter, Ava P. Amini, Lorin Crawford
{"title":"Multimodal cell foundation models require synergistic integration beyond alignment","authors":"Till Richter, Eric Zimmermann, James Hall, Fabian J. Theis, Srivatsan Raghavan, Peter S. Winter, Ava P. Amini, Lorin Crawford","doi":"10.1038/s42256-026-01328-3","DOIUrl":"https://doi.org/10.1038/s42256-026-01328-3","url":null,"abstract":"Integrating measurements across modalities and scales into unified quantitative frameworks of cellular function is a central goal in computational biology. Although powerful unimodal foundation models exist, the scarcity of large-scale paired data limits joint multimodal training. This constraint favours compositional foundation models, which fuse frozen unimodal experts through a learned interface. However, it remains unclear when such fusion provides task-relevant information beyond the strongest unimodal representation rather than merely aggregating redundant signal. Here we introduce Synergistic Information Score, a metric grounded in partial information decomposition that quantifies information gain arising only from cross-modal interactions. Extending theory from self-supervised learning, we show that standard alignment-based objectives with frozen encoders collapse to detect linear redundancies, which constrains their ability to capture nonlinear synergistic states. This distinction is especially important for tasks that connect tissue morphology with gene expression. Benchmarking ten fusion methods on spatial transcriptomics datasets, we demonstrate that tasks dominated by linear redundancies are well served by unimodal baselines, whereas complex niche definitions benefit from synergy-aware integration. Finally, we perform a scaling analysis and show that fine-tuning a dominant unimodal expert is the most sample-efficient strategy for standard tasks. Together, these results suggest that progress in multimodal modelling of cellular state requires shifting from alignment-based objectives to synergy-driven integration that exploits complementary cross-modal signal.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"29 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2026-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149397196","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":"Fractal basin geometry and the limits to predictability and reproducibility in deep learning","authors":"Andrew Ly, Pulin Gong","doi":"10.1038/s42256-026-01336-3","DOIUrl":"https://doi.org/10.1038/s42256-026-01336-3","url":null,"abstract":"Fundamental limits to predictability are central to our understanding of many physical and computational systems. In deep learning, training outcomes are often difficult to predict and reproduce even when extrinsic sources of randomness are controlled, yet the underlying mechanism remains unclear. Here we propose riddled basin geometry as a unifying dynamical systems mechanism: every initialization leading to one solution lies arbitrarily close to initializations leading to different solutions, forming a fat fractal with structure at arbitrarily fine scales. Using a minimal neural network model, we analytically establish the classical route to riddling and derive a near-zero uncertainty exponent: even sharp increases in initialization precision yield only marginal gains in outcome predictability. In deep networks, intertwined training destinations and near-zero parameter-space exponents provide robust signatures consistent with riddling across the tested architectures, optimizers and training protocols, offering a common dynamical account of otherwise disparate empirical observations. We further introduce functional uncertainty exponents, extending these diagnostics of scale-insensitive irreproducibility from parameter space to the learned functions themselves. Together, our results support riddled basin geometry as a candidate organizing principle for irreproducibility in deep learning, with practical implications for optimization and the reliable deployment of artificial intelligence.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"15 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2026-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149359565","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}
Ting-Hsiang Hsu (徐鼎翔), Baihong Zhou (周柏宏), Qibin Liu (刘齐斌), Yue Xu (许悦), Shu Li (李数), George Wei-Shu Hou (侯維恕), Benjamin Nachman, Shih-Chieh Hsu (徐士傑), Vinicius Mikuni, Yuan-Tang Chou (周圓唐), Yulei Zhang (张宇雷)
{"title":"Foundation model for particle collision data analysis","authors":"Ting-Hsiang Hsu \u0000 (徐鼎翔), Baihong Zhou \u0000 (周柏宏), Qibin Liu \u0000 (刘齐斌), Yue Xu \u0000 (许悦), Shu Li \u0000 (李数), George Wei-Shu Hou \u0000 (侯維恕), Benjamin Nachman, Shih-Chieh Hsu \u0000 (徐士傑), Vinicius Mikuni, Yuan-Tang Chou \u0000 (周圓唐), Yulei Zhang \u0000 (张宇雷)","doi":"10.1038/s42256-026-01322-9","DOIUrl":"https://doi.org/10.1038/s42256-026-01322-9","url":null,"abstract":"Data-intensive collider experiments increasingly require models that transfer across high-dimensional, partially observed measurements, yet most analyses still optimize separate models for each task. Here, to address this bottleneck, we introduce EVENET, an event-level foundation model pretrained on 500 million simulated collision events using self-supervised learning and physics-informed supervision. The model constructs a shared particle-cloud representation from the variable-length set of physics objects in each event. Across searches for heavy resonances and exotic Higgs decays, EVENET outperforms both established and state-of-the-art baselines, particularly in low-statistics regimes. We validate transfer to experimental data by rediscovering the ϒ meson in CMS Open Data. The pretrained model also supports precise extraction of quantum-correlation observables that remain stable under the tested systematic variations. Together, these results establish a reusable backbone for diverse collider analyses, improving downstream adaptation after a substantial one-time pretraining investment.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"34 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2026-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149305490","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":"Efficient equivariant framework for universal charge density prediction","authors":"Xiwen Li, Zaizhou Xin, Hongyu Yu, Yang Zhong, Liangliang Hong, Xingao Gong, Hongjun Xiang","doi":"10.1038/s42256-026-01326-5","DOIUrl":"https://doi.org/10.1038/s42256-026-01326-5","url":null,"abstract":"Accelerating materials discovery requires efficient electronic structure calculations, which remain a critical challenge owing to the high computational cost of density functional theory. While charge density plays a central role in determining electronic structures in density functional theory, existing generalizable machine learning (ML) charge density models are hindered by prohibitive computational costs. Here we present the Equivariant Density Graph Neural Network (EdenGNN), an ML charge density model for electronic structure to overcome these limitations. It predicts both charge density and augmentation occupancies, enabling electronic structure calculations with projector augmented-wave accuracy. Critically, by using a basis-expansion formulation with fully trainable radial basis functions and a Δ-learning strategy to capture charge transfer, it is more than an order of magnitude faster. Notably, trained on the Materials Project database, our universal model for non-magnetic structures across the periodic table, EdenGNN-Uni, accurately predicts the band structures for most unseen materials across a vast chemical space, demonstrating enhanced robustness over universal ML Hamiltonian methods. These findings establish the ML charge density model as a scalable ab initio method for large-scale electronic structure calculations and high-throughput screening.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2026-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149241772","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}
Jingdi Wan, Hongping Wang, Bo Liu, Xiaolei Yang, Xiaodong Hu, Shengze Cai, Guowei He, Yang Liu
{"title":"Lagrangian–Eulerian learning of flow field and trajectories with TrajectoryFlowNet","authors":"Jingdi Wan, Hongping Wang, Bo Liu, Xiaolei Yang, Xiaodong Hu, Shengze Cai, Guowei He, Yang Liu","doi":"10.1038/s42256-026-01316-7","DOIUrl":"https://doi.org/10.1038/s42256-026-01316-7","url":null,"abstract":"Predicting particle transport in complex flows is traditionally achieved by solving the Navier–Stokes equations. Numerical and experimental methods typically require deep physical insights and incur high computational costs. Although machine learning offers an alternative, existing approaches fail to generalize the prediction of long-range particle trajectories in sparse data regimes. Here, to this end, we propose TrajectoryFlowNet, a Lagrangian–Eulerian physics-informed neural network architecture, for fluid flow velocimetry and imaging via learning to predict spatiotemporal flow fields and long-range particle trajectories. The salient features of our model include its ability to handle complex flow patterns with irregular boundaries, predict the full-field flows, image the long-range flow trajectory of any arbitrary particle, and ensure physical consistency in predictions based on only scarce measurement of flow trajectories. We validate TrajectoryFlowNet via both numerical examples (for example, lid-driven cavity flow and complex cylinder flow) and experimental test cases (for example, aortic and ventricle blood flows) across diverse flow scenarios. The results demonstrate our model’s effectiveness in capturing intricate particle-laden flow dynamics, enabling long-range tracking of particles and accurate construction of flow fields in real-world applications.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"494 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149241867","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":"Towards understanding and monitorability of reasoning LLMs","authors":"","doi":"10.1038/s42256-026-01333-6","DOIUrl":"10.1038/s42256-026-01333-6","url":null,"abstract":"Frontier LLMs are trained to solve problems in a step-by-step way, generating reasoning text in human-understandable language. However, these reasoning tokens are not accurate explanations of LLMs’ internal computations, raising challenges for monitorability.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 10","pages":"1507-1507"},"PeriodicalIF":29.8,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-026-01333-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219602","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}
Xabier Martínez-de-Morentin, Sumeer A. Khan, Itziar Cenzano, Robert Lehmann, Alberto Maillo, Vincenzo Lagani, Jesper Tegner, David Gomez-Cabrero
{"title":"Reusability report: multi-sample omics network inference operates in distinct robustness regimes defined by prior knowledge and data availability","authors":"Xabier Martínez-de-Morentin, Sumeer A. Khan, Itziar Cenzano, Robert Lehmann, Alberto Maillo, Vincenzo Lagani, Jesper Tegner, David Gomez-Cabrero","doi":"10.1038/s42256-026-01311-y","DOIUrl":"10.1038/s42256-026-01311-y","url":null,"abstract":"Knowledge-constrained network inference enables the reconstruction of regulatory programmes from high-dimensional biological data, yet the conditions under which shared and context-specific structures can be reliably identified remain poorly understood. Pablo Rodriguez-Mier et al. recently introduced CORNETO, a framework for multi-sample constrained inference. Here we reproduce, evaluate and extend CORNETO in terms of robustness, identifiability and bias–variance trade-offs. Using dynamic haematopoiesis and stable cortical datasets, we systematically assess four network reconstruction paradigms while preserving the original method-specific evaluation procedures and benchmark definitions. We show that multi-sample inference generally improves robustness and reproducibility, although gains in predictive performance depend on biological context and the completeness of the prior network. To enhance stability, we introduce bootstrap aggregation and selective re-expansion strategies that improve consensus robustness and recovery while preserving context-specific signals without modifying the underlying optimization scheme or sacrificing generality. Across datasets and methods, our results reveal distinct inference regimes governed by sample availability, prior knowledge and regularization. Together, these findings position network reconstruction as a regime-dependent learning problem and provide practical principles for robust multi-sample biological network inference. This work studies the reusability of CORNETO, a previously developed framework for learning biological networks from multi-omics data. Robust network inference is found to depend on data availability, prior knowledge, regularization and biological context.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 10","pages":"1616-1631"},"PeriodicalIF":29.8,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-026-01311-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149219603","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}
Luyang Cao, Zhijian Wu, Jian Zhang, Lei Qi, Yang Gao, Hairong Zheng, Yefeng Zheng, Yinghuan Shi
{"title":"An all-in-one foundation model for multimodal medical image restoration and enhancement","authors":"Luyang Cao, Zhijian Wu, Jian Zhang, Lei Qi, Yang Gao, Hairong Zheng, Yefeng Zheng, Yinghuan Shi","doi":"10.1038/s42256-026-01310-z","DOIUrl":"10.1038/s42256-026-01310-z","url":null,"abstract":"Medical image quality is essential for reliable clinical diagnosis and downstream artificial intelligence analysis, yet routine images are often degraded by noise, motion artefacts, low contrast, low-dose acquisition or modality-specific artefacts. Here we present AMIFound, an all-in-one foundation model for medical image enhancement and restoration across computed tomography, magnetic resonance imaging, positron emission tomography, endoscopy, ultrasound, fundus imaging and X-ray. AMIFound is trained and evaluated on 3.76 million paired high-quality and degraded images spanning 7 representative degradation patterns. A shared encoder captures modality and degradation cues, while a dynamically routed expert restoration pool adapts the enhancement pathway for each input. Across 7 modalities, AMIFound outperforms 38 task-specific and generalist baselines on full-reference image quality metrics, clinician assessment and robustness tests under combined degradations as well as on naturally degraded clinical images. Enhanced images further improve 44 disease detection tasks, tumour stage prediction and survival risk stratification in non-small-cell lung cancer, including improved individual-level prognostic ranking. These results support AMIFound as a domain-specific foundation model for improving low-quality clinical images and strengthening downstream medical artificial intelligence workflows while preserving clinically relevant information. Cao et al. present AMIFound, a foundation model that unifies medical image restoration across seven imaging modalities, delivering robust enhancement across diverse degradations and preserving clinically relevant information for diagnosis.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"8 10","pages":"1596-1615"},"PeriodicalIF":29.8,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149209405","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}