@inproceedings{21949, abstract = {Cardiac T1 mapping provides critical quantitative insights into myocardial tissue composition, enabling the assessment of pathologies such as fibrosis, inflammation, and edema. However, the inherently dynamic nature of the heart imposes strict limits on acquisition times, making high-resolution T1 mapping a persistent challenge. Compressed sensing (CS) approaches have reduced scan durations by undersampling k-space and reconstructing images from partial data, and recent studies show that jointly optimizing the undersampling patterns with the reconstruction network can substantially improve performance. Still, most current T1 mapping pipelines rely on static, hand-crafted masks that do not exploit the full acceleration and accuracy potential. Furthermore, most existing methods do not levarage the physical T1 decay model in optimization. In this work, we introduce T1- PILOT: an end-to-end method that explicitly incorporates the T1 signal relaxation model into the sampling–reconstruction framework to guide the learning of non-Cartesian trajectories, cross-frame alignment, and T1 decay estimation. Through extensive experiments on the CMRxRecon dataset, T1-PILOT significantly outperforms several baseline strategies (including learned single-mask and fixed radial or golden-angle sampling schemes), achieving higher T1 map fidelity at greater acceleration factors. In particular, we observe consistent gains in PSNR and VIF relative to existing methods, along with marked improvements in delineating finer myocardial structures. Our results highlight that optimizing sampling trajectories in tandem with the physical relaxation model leads to both enhanced quantitative accuracy and reduced acquisition times. Code for reproducing all experiments and results is available at https://github.com/tamirshor7/T1-PILOT}, author = {Shor, Tamir and Freiman, Moti and Baskin, Chaim and Bronstein, Alexander}, booktitle = {Medical Imaging with Deep Learning}, issn = {2640-3498}, keywords = {Cardiac T1 Mapping, Trajectory Optimization and Reconstruction, PhysicsInformed Deep-Learning}, location = {Taipei, Taiwan}, pages = {1969--1982}, publisher = {ML Research Press}, title = {{T1-PILOT: Physics-informed learned optimized trajectories for T1 mapping acceleration}}, volume = {315}, year = {2026}, } @article{21246, abstract = {Stellar astrophysics relies on diverse observational modalities—primarily photometric light curves and spectroscopic data—from which fundamental stellar properties are inferred. While machine learning (ML) has advanced analysis within individual modalities, the complementary information encoded across modalities remains largely underexploited. We present the dual embedding for stellar astronomy (DESA) model, a novel multimodal foundation model that integrates light curves and spectra to learn a unified, physically meaningful latent space for stars. DESA first trains separate modality-specific encoders using a hybrid supervised/self-supervised scheme, and then aligns them through DualFormer, a transformer-based cross-modal integration module tailored for astrophysical data. DualFormer combines cross- and self-attention, a novel dual-projection alignment loss, and a projection-space eigendecomposition that yields physically structured embeddings. We demonstrate that DESA significantly outperforms leading unimodal and self-supervised baselines across a range of tasks. In zero- and few-shot settings, DESA’s learned representations recover stellar color–magnitude and Hertzsprung–Russell diagrams with high fidelity (R2 = 0.92 for photometric regressions). In full fine-tuning, DESA achieves state-of-the-art accuracy for binary star detection (AUC = 0.99, AP = 1.00) and stellar age prediction (RMSE = 0.94 Gyr). As a compelling case, DESA naturally separates synchronized binaries from young stars—two populations with nearly identical light curves—purely from their embedded positions in UMAP space, without requiring external kinematic or luminosity information. DESA thus offers a powerful new framework for multimodal, data-driven stellar population analysis, enabling both accurate prediction and novel discovery.}, author = {Kamai, Ilay and Bronstein, Alexander and Perets, Hagai B.}, issn = {1538-4357}, journal = {The Astrophysical Journal}, publisher = {IOP Publishing}, title = {{Machine Learning inference of stellar properties using integrated photometric and spectroscopic data}}, doi = {10.3847/1538-4357/ae0cbc}, volume = {994}, year = {2025}, } @inproceedings{21327, abstract = {Proteins exist as a dynamic ensemble of multiple conformations, and these motions are often crucial for their functions. However, current structure prediction methods predominantly yield a single conformation, overlooking the conformational heterogeneity revealed by diverse experimental modalities. Here, we present a framework for building experiment-grounded protein structure generative models that infer conformational ensembles consistent with measured experimental data. The key idea is to treat stateof-the-art protein structure predictors (e.g., AlphaFold3) as sequence-conditioned structural priors, and cast ensemble modeling as posterior inference of protein structures given experimental measurements. Through extensive real-data experiments, we demonstrate the generality of our method to incorporate a variety of experimental measurements. In particular, our framework uncovers previously unmodeled conformational heterogeneity from crystallographic densities, and generates high-accuracy NMR ensembles orders of magnitude faster than the status quo. Notably, we demonstrate that our ensembles outperform AlphaFold3 (Abramson et al., 2024) and sometimes better fit experimental data than publicly deposited structures to the Protein Data Bank (PDB, Burley et al. (2017)). We believe that this approach will unlock building predictive models that fully embrace experimentally observed conformational diversity.}, author = {Maddipatla, Sai A and Sellam, Nadav E and Bojan, Meital I and Vedula, Sanketh and Schanda, Paul and Marx, Ailie and Bronstein, Alexander}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, issn = {2640-3498}, location = {Vancouver, Canada}, pages = {42366 -- 42393}, publisher = {ML Research Press}, title = {{Inverse problems with experiment-guided AlphaFold}}, volume = {267}, year = {2025}, } @article{19595, abstract = {We investigate the locality of magnetic response in polycyclic aromatic molecules using a novel deep-learning approach. Our method employs graph neural networks (GNNs) with a graph-of-rings representation to predict nucleus independent chemical shifts (NICS) in the space around the molecule. We train a series of models, each time reducing the size of the largest molecules used in training. The accuracy of prediction remains high (MAE < 0.5 ppm), even when training the model only on molecules with up to four rings, thus providing strong evidence for the locality of magnetic response. To overcome the known problem of generalization of GNNs, we implement a k-hop expansion strategy and succeed in achieving accurate predictions for molecules with up to 15 rings (almost 4 times the size of the largest training example). Our findings have implications for understanding the magnetic response in complex molecules and demonstrate a promising approach to overcoming GNN scalability limitations. Furthermore, the trained models enable rapid characterization, without the need for more expensive DFT calculations.}, author = {Davidson, Yair and Philipp, Aviad and Chakraborty, Sabyasachi and Bronstein, Alexander and Gershoni-Poranne, Renana}, issn = {1089-7690}, journal = {Journal of Chemical Physics}, number = {14}, publisher = {AIP Publishing}, title = {{How local is “local”? Deep learning reveals locality of the induced magnetic field of polycyclic aromatic hydrocarbons}}, doi = {10.1063/5.0257558}, volume = {162}, year = {2025}, } @article{20100, abstract = {A key step in protein structure prediction involves the detection of co-evolving pairs of residues, a signal for spatial proximity. This information is gleaned from multiple sequence alignment and underscores Alphafold’s structure prediction for almost every known protein. A simple means to create proteins beyond those found in nature, is by unnaturally fusing together two known proteins or protein parts. Here we demonstrate that structured peptides are predicted with significantly reduced accuracy when added to the terminal ends of scaffold proteins. Appending the multiple sequence alignment for the individual peptide tags to that of the scaffold protein often restores prediction accuracy. This work suggests that this windowed multiple sequence alignment approach can be a useful tool for predicting the structure of fused, chimeric proteins.}, author = {Vedula, Sanketh and Bronstein, Alexander and Marx, Ailie}, issn = {2001-0370}, journal = {Computational and Structural Biotechnology Journal}, pages = {3292--3298}, publisher = {Elsevier}, title = {{Improving prediction accuracy in chimeric proteins with windowed multiple sequence alignment}}, doi = {10.1016/j.csbj.2025.07.039}, volume = {27}, year = {2025}, } @misc{20103, abstract = {Official implementation, windowed MSAs, and the predictions as reported in the manuscript titled "Improving Prediction Accuracy in Chimeric Proteins with Windowed Multiple Sequence Alignment". (2025-06-27)}, author = {Vedula, Sanketh and Bronstein, Alexander and Marx, Ailie}, publisher = {Harvard Dataverse}, title = {{Replication Data for: "Improving Prediction Accuracy in Chimeric Proteins with Windowed Multiple Sequence Alignment"}}, doi = {10.7910/DVN/DYEBVM}, year = {2025}, } @inproceedings{20707, abstract = {Understanding physiological responses during running is critical for performance optimization, tailored training prescriptions, and athlete health management. We introduce a comprehensive framework—what we believe to be the first capable of predicting instantaneous oxygen consumption (VO2) trajectories exclusively from consumer-grade wearable data. Our approach employs two complementary physiological models: (1) accurate modeling of heart rate (HR) dynamics via a physiologically constrained ordinary differential equation (ODE) and neural Kalman filter, trained on over 3 million HR observations, achieving 1-second interval predictions with mean absolute errors as low as 2.81 bpm (correlation 0.87); and (2) leveraging the principles of precise HR modeling, a novel VO2 prediction architecture requiring only the initial second of VO2 data for calibration, enabling robust, sequence-to-sequence metabolic demand estimation. Despite relying solely on smartwatch and chest-strap data, our method achieves mean absolute percentage errors of approximately 13%, effectively capturing rapid physiological transitions and steady-state conditions across diverse running intensities. Our synchronized dataset, complemented by blood lactate measurements, further lays the foundation for future noninvasive metabolic zone identification. By embedding physiological constraints within modern machine learning, this framework democratizes advanced metabolic monitoring, bridging laboratory-grade accuracy and everyday accessibility, thus empowering both elite athletes and recreational fitness enthusiasts.}, author = {Gahtan, Barak and Vedula, Sanketh and Samuelly Leichtag, Gil and Kodesh, Einat and Bronstein, Alexander}, booktitle = {Proceedings of the 27th International Conference on Multimodal Interaction}, isbn = {9798400714993}, location = {Canberra, Australia}, pages = {60--77}, publisher = {Association for Computing Machinery}, title = {{From lab to wrist: Bridging metabolic monitoring and consumer wearables for heart rate and oxygen consumption modeling}}, doi = {10.1145/3716553.3750815}, year = {2025}, } @article{18203, abstract = {Protein Data Bank (PDB) files list the relative spatial location of atoms in a protein structure as the final output of the process of fitting and refining to experimentally determined electron density measurements. Where experimental evidence exists for multiple conformations, atoms are modelled in alternate locations. Programs reading PDB files commonly ignore these alternate conformations by default leaving users oblivious to the presence of alternate conformations in the structures they analyze. This has led to underappreciation of their prevalence, under characterisation of their features and limited the accessibility to this high-resolution data representing structural ensembles. We have trawled PDB files to extract structural features of residues with alternately located atoms. The output includes the distance between alternate conformations and identifies the location of these segments within the protein chain and in proximity of all other atoms within a defined radius. This dataset should be of use in efforts to predict multiple structures from a single sequence and support studies investigating protein flexibility and the association with protein function.}, author = {Rosenberg, Aviv A. and Marx, Ailie and Bronstein, Alexander}, issn = {2052-4463}, journal = {Scientific Data}, publisher = {Springer Nature}, title = {{A dataset of alternately located segments in protein crystal structures}}, doi = {10.1038/s41597-024-03595-4}, volume = {11}, year = {2024}, } @article{18204, abstract = {Non-linear dynamical systems describe numerous real-world phenomena, ranging from the weather, to financial markets and disease progression. Individual systems may share substantial common information, for example patients’ anatomy. Lately, deep-learning has emerged as a leading method for data-driven modeling of non-linear dynamical systems. Yet, despite recent breakthroughs, prior works largely ignored the existence of shared information between different systems. However, such cases are quite common, for example, in medicine: we may wish to have a patient-specific model for some disease, but the data collected from a single patient is usually too small to train a deep-learning model. Hence, we must properly utilize data gathered from other patients. Here, we explicitly consider such cases by jointly modeling multiple systems. We show that the current single-system models consistently fail when trying to learn simultaneously from multiple systems. We suggest a framework for jointly approximating the Koopman operators of multiple systems, while intrinsically exploiting common information. We demonstrate how we can adapt to a new system using order-of-magnitude less new data and show the superiority of our model over competing methods, in terms of both forecasting ability and statistical fidelity, across chaotic, cardiac, and climate systems.}, author = {Elul, Yonatan and Rozenberg, Eyal and Boyarski, Amit and Yaniv, Yael and Schuster, Assaf and Bronstein, Alexander}, issn = {2399-3650}, journal = {Communications Physics}, publisher = {Springer Nature}, title = {{Data-driven modeling of interrelated dynamical systems}}, doi = {10.1038/s42005-024-01626-5}, volume = {7}, year = {2024}, } @article{18205, abstract = {We explore numerically an unsupervised, physics-informed, deep learning-based reconstruction technique for time-resolved imaging by multiplexed ptychography. In our method, the untrained deep learning model replaces the iterative algorithm’s update step, yielding superior reconstructions of multiple dynamic object frames compared to conventional methodologies. More precisely, we demonstrate improvements in image quality and resolution, while reducing sensitivity to the number of recorded frames, the mutual orthogonality of different probe modes, overlap between neighboring probe beams and the cutoff frequency of the ptychographic microscope – properties that are generally of paramount importance for ptychographic reconstruction algorithms.}, author = {Wengrowicz, Omri and Bronstein, Alexander and Cohen, Oren}, issn = {1094-4087}, journal = {Optics Express}, number = {6}, pages = {8791--8803}, publisher = {Optica Publishing Group}, title = {{Unsupervised physics-informed deep learning-based reconstruction for time-resolved imaging by multiplexed ptychography}}, doi = {10.1364/oe.515445}, volume = {32}, year = {2024}, } @inproceedings{18206, abstract = {In the context of in vitro fertilization (IVF), selecting embryos for transfer is critical in determining pregnancy outcomes, with implantation as the essential first milestone for a successful pregnancy. This study introduces the Bonna algorithm, an advanced deep-learning framework engineered to predict embryo implantation probabilities. The algorithm employs a sophisticated integration of machine-learning techniques, utilizing MobileNetV2 for pixel and context embedding, a custom Pix2Pix model for precise segmentation, and a Vision Transformer for additional depth in embedding. MobileNetV2 was chosen for its robust feature extraction capabilities, focusing on textures and edges. The custom Pix2Pix model is adapted for precise segmentation of significant biological features such as the zona pellucida and blastocyst cavity. The Vision Transformer adds a global perspective, capturing complex patterns not apparent in local image segments. Tested on a dataset of images of human blastocysts collected from Ukraine, Israel, and Spain, the Bonna algorithm was rigorously validated through 10-fold cross-validation to ensure its robustness and reliability. It demonstrates superior performance with a mean area under the receiver operating characteristic curve (AUC) of 0.754, significantly outperforming existing models. The study not only advances predictive accuracy in embryo selection but also highlights the algorithm’s clinical applicability due to reliable confidence reporting.}, author = {Rave, Gilad and Fordham, Daniel E. and Bronstein, Alexander and Silver, David H.}, booktitle = {First International Conference on Artificial Intelligence in Healthcare}, isbn = {9783031672842}, issn = {1611-3349}, location = {Swansea, United Kingdom}, pages = {160--171}, publisher = {Springer Nature}, title = {{Enhancing predictive accuracy in embryo implantation: The Bonna algorithm and its clinical implications}}, doi = {10.1007/978-3-031-67285-9_12}, volume = {14976}, year = {2024}, } @article{18207, abstract = {Comparison of myoglobin structures reveals that protein isolated from horse heart consistently adopts an alternate turn conformation in comparison to its homologues. Analysis of hundreds of high-resolution structures discounts crystallization conditions or the surrounding amino acid protein environment as explaining this difference, that is also not captured by the AlphaFold prediction. Rather, a water molecule is identified as stabilizing the conformation in the horse heart structure, which immediately reverts to the whale conformation in molecular dynamics simulations excluding that structural water.}, author = {Bronstein, Alexander and Marx, Ailie}, issn = {2045-2322}, journal = {Scientific Reports}, publisher = {Springer Nature}, title = {{Water stabilizes an alternate turn conformation in horse heart myoglobin}}, doi = {10.1038/s41598-023-32821-z}, volume = {13}, year = {2023}, } @article{18208, abstract = {The holy grail of materials science is de novo molecular design, meaning engineering molecules with desired characteristics. The introduction of generative deep learning has greatly advanced efforts in this direction, yet molecular discovery remains challenging and often inefficient. Herein we introduce GaUDI, a guided diffusion model for inverse molecular design that combines an equivariant graph neural net for property prediction and a generative diffusion model. We demonstrate GaUDI’s effectiveness in designing molecules for organic electronic applications by using single- and multiple-objective tasks applied to a generated dataset of 475,000 polycyclic aromatic systems. GaUDI shows improved conditional design, generating molecules with optimal properties and even going beyond the original distribution to suggest better molecules than those in the dataset. In addition to point-wise targets, GaUDI can also be guided toward open-ended targets (for example, a minimum or maximum) and in all cases achieves close to 100% validity of generated molecules.}, author = {Weiss, Tomer and Mayo Yanes, Eduardo and Chakraborty, Sabyasachi and Cosmo, Luca and Bronstein, Alexander and Gershoni-Poranne, Renana}, issn = {2662-8457}, journal = {Nature Computational Science}, number = {10}, pages = {873--882}, publisher = {Springer Nature}, title = {{Guided diffusion for inverse molecular design}}, doi = {10.1038/s43588-023-00532-0}, volume = {3}, year = {2023}, } @article{18209, abstract = {In this work, interpretable deep learning was used to identify structure–property relationships governing the HOMO–LUMO gap and the relative stability of polybenzenoid hydrocarbons (PBHs) using a ring-based graph representation. This representation was combined with a subunit-based perception of PBHs, allowing chemical insights to be presented in terms of intuitive and simple structural motifs. The resulting insights agree with conventional organic chemistry knowledge and electronic structure-based analyses and also reveal new behaviors and identify influential structural motifs. In particular, we evaluated and compared the effects of linear, angular, and branching motifs on these two molecular properties and explored the role of dispersion in mitigating the torsional strain inherent in nonplanar PBHs. Hence, the observed regularities and the proposed analysis contribute to a deeper understanding of the behavior of PBHs and form the foundation for design strategies for new functional PBHs.}, author = {Weiss, Tomer and Wahab, Alexandra and Bronstein, Alexander and Gershoni-Poranne, Renana}, issn = {1520-6904}, journal = {The Journal of Organic Chemistry}, number = {14}, pages = {9645--9656}, publisher = {American Chemical Society}, title = {{Interpretable deep-learning unveils structure–property relationships in polybenzenoid hydrocarbons}}, doi = {10.1021/acs.joc.2c02381}, volume = {88}, year = {2023}, } @inproceedings{18212, abstract = {The high memory bandwidth demand of sparse embedding layers continues to be a critical challenge in scaling the performance of recommendation models. While prior works have exploited heterogeneous memory system designs and partial embedding sum memoization techniques, they offer limited benefits. This is because prior designs either target a very small subset of embeddings to simplify their analysis or incur a high processing cost to account for all embeddings, which does not scale with the large sizes of modern embedding tables. This paper proposes GRACE-a lightweight and scalable graph-based algorithm-system co-design framework to significantly improve the embedding layer performance of recommendation models. GRACE proposes a novel Item Co-occurrence Graph (ICG) that scalably records item co-occurrences. GRACE then presents a new system-aware ICG clustering algorithm to find frequently accessed item combinations of arbitrary lengths to compute and memoize their partial sums. High-frequency partial sums are stored in a software-managed cache space to reduce memory traffic and improve the throughput of computing sparse features. We further present a cache data layout and low-cost address computation logic to efficiently lookup item embeddings and their partial sums. Our evaluation shows that GRACE significantly outperforms the state-of-the-art techniques SPACE and MERCI by 1.5x and 1.4x, respectively.}, author = {Ye, Haojie and Vedula, Sanketh and Chen, Yuhan and Yang, Yichen and Bronstein, Alexander and Dreslinski, Ronald and Mudge, Trevor and Talati, Nishil}, booktitle = {Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems}, isbn = {9781450399180}, number = {3}, pages = {282--301}, publisher = {Association for Computing Machinery}, title = {{GRACE: A scalable graph-based approach to accelerating recommendation model inference}}, doi = {10.1145/3582016.3582029}, volume = {11}, year = {2023}, } @article{18213, abstract = {What is the best way to match the nodes of two graphs? This graph alignment problem generalizes graph isomorphism and arises in applications from social network analysis to bioinformatics. Some solutions assume that auxiliary information on known matches or node or edge attributes is available, or utilize arbitrary graph features. Such methods fare poorly in the pure form of the problem, in which only graph structures are given. Other proposals translate the problem to one of aligning node embeddings, yet, by doing so, provide only a single-scale view of the graph. In this article, we transfer the shape-analysis concept of functional maps from the continuous to the discrete case, and treat the graph alignment problem as a special case of the problem of finding a mapping between functions on graphs. We present GRASP, a method that first establishes a correspondence between functions derived from Laplacian matrix eigenvectors, which capture multiscale structural characteristics, and then exploits this correspondence to align nodes. We enhance the basic form of GRASP by altering two of its components, namely the embedding method and the assignment procedure it employs, leveraging its modular, hence adaptable design. Our experimental study, featuring noise levels higher than anything used in previous studies, shows that the enhanced form of GRASP outperforms scalable state-of-the-art methods for graph alignment across noise levels and graph types, and performs competitively with respect to the best non-scalable ones. We include in our study another modular graph alignment algorithm, CONE, which is also adaptable thanks to its modular nature, and show it can manage graphs with skewed power-law degree distributions.}, author = {Hermanns, Judith and Skitsas, Konstantinos and Tsitsulin, Anton and Munkhoeva, Marina and Kyster, Alexander and Nielsen, Simon and Bronstein, Alexander and Mottin, Davide and Karras, Panagiotis}, issn = {1556-472X}, journal = {ACM Transactions on Knowledge Discovery from Data}, number = {4}, publisher = {Association for Computing Machinery}, title = {{GRASP: Scalable graph alignment by spectral corresponding functions}}, doi = {10.1145/3561058}, volume = {17}, year = {2023}, } @article{18214, abstract = {Graph sparsification is a technique that approximates a given graph by a sparse graph with a subset of vertices and/or edges. The goal of an effective sparsification algorithm is to maintain specific graph properties relevant to the downstream task while minimizing the graph's size. Graph algorithms often suffer from long execution time due to the irregularity and the large real-world graph size. Graph sparsification can be applied to greatly reduce the run time of graph algorithms by substituting the full graph with a much smaller sparsified graph, without significantly degrading the output quality. However, the interaction between numerous sparsifiers and graph properties is not widely explored, and the potential of graph sparsification is not fully understood. In this work, we cover 16 widely-used graph metrics, 12 representative graph sparsification algorithms, and 14 real-world input graphs spanning various categories, exhibiting diverse characteristics, sizes, and densities. We developed a framework to extensively assess the performance of these sparsification algorithms against graph metrics, and provide insights to the results. Our study shows that there is no one sparsifier that performs the best in preserving all graph properties, e.g. sparsifiers that preserve distance-related graph properties (eccentricity) struggle to perform well on Graph Neural Networks (GNN). This paper presents a comprehensive experimental study evaluating the performance of sparsification algorithms in preserving essential graph metrics. The insights inform future research in incorporating matching graph sparsification to graph algorithms to maximize benefits while minimizing quality degradation. Furthermore, we provide a framework to facilitate the future evaluation of evolving sparsification algorithms, graph metrics, and ever-growing graph data.}, author = {Chen, Yuhan and Ye, Haojie and Vedula, Sanketh and Bronstein, Alexander and Dreslinski, Ronald and Mudge, Trevor and Talati, Nishil}, issn = {2150-8097}, journal = {Proceedings of the VLDB Endowment}, number = {3}, pages = {427--440}, publisher = {Association for Computing Machinery}, title = {{Demystifying graph sparsification algorithms in graph properties preservation}}, doi = {10.14778/3632093.3632106}, volume = {17}, year = {2023}, } @inproceedings{18215, abstract = {We study the problem of real-time scheduling in a multi-hop millimeter-wave (mmWave) mesh. We develop a model-free deep reinforcement learning algorithm called Adaptive Activator RL (AARL), which determines the subset of mmWave links that should be activated during each time slot and the power level for each link. The most important property of AARL is its ability to make scheduling decisions within the strict time frame constraints of typical 5G mmWave networks. AARL can handle a variety of network topologies, network loads, and interference models, it can also adapt to different workloads. We demonstrate the operation of AARL on several topologies: a small topology with 10 links, a moderately-sized mesh with 48 links, and a large topology with 96 links. We show that for each topology, we compare the throughput obtained by AARL to that of a benchmark algorithm called RPMA (Residual Profit Maximizer Algorithm). The most important advantage of AARL compared to RPMA is that it is much faster and can make the necessary scheduling decisions very rapidly during every time slot, while RPMA cannot. In addition, the quality of the scheduling decisions made by AARL outperforms those made by RPMA.}, author = {Gahtan, Barak and Cohen, Reuven and Bronstein, Alexander and Kedar, Gil}, booktitle = {14th International Conference on Network of the Future}, isbn = {9798350338089}, issn = {2833-0072}, location = {Izmir, Turkiye}, pages = {71--79}, publisher = {IEEE}, title = {{Using deep reinforcement learning for mmWave real-time scheduling}}, doi = {10.1109/nof58724.2023.10302794}, year = {2023}, } @article{18216, abstract = {Protein structure, both at the global and local level, dictates function. Proteins fold from chains of amino acids, forming secondary structures, α-helices and β-strands, that, at least for globular proteins, subsequently fold into a three-dimensional structure. Here, we show that a Ramachandran-type plot focusing on the two dihedral angles separated by the peptide bond, and entirely contained within an amino acid pair, defines a local structural unit. We further demonstrate the usefulness of this cross-peptide-bond Ramachandran plot by showing that it captures β-turn conformations in coil regions, that traditional Ramachandran plot outliers fall into occupied regions of our plot, and that thermophilic proteins prefer specific amino acid pair conformations. Further, we demonstrate experimentally that the effect of a point mutation on backbone conformation and protein stability depends on the amino acid pair context, i.e., the identity of the adjacent amino acid, in a manner predictable by our method.}, author = {Rosenberg, Aviv A. and Yehishalom, Nitsan and Marx, Ailie and Bronstein, Alexander}, issn = {1091-6490}, journal = {Proceedings of the National Academy of Sciences}, number = {44}, publisher = {National Academy of Sciences}, title = {{An amino-domino model described by a cross-peptide-bond Ramachandran plot defines amino acid pairs as local structural units}}, doi = {10.1073/pnas.2301064120}, volume = {120}, year = {2023}, } @inproceedings{18217, abstract = {A central challenge in building robotic prostheses is the creation of a sensor-based system able to read physiological signals from the lower limb and instruct a robotic hand to perform various tasks. Existing systems typically perform discrete gestures such as pointing or grasping, by employing electromyography (EMG) or ultrasound (US) technologies to analyze muscle states. While estimating finger gestures has been done in the past by detecting prominent gestures, we are interested in detection, or inference, done in the context of fine motions that evolve over time. Examples include motions occurring when performing fine and dexterous tasks such as keyboard typing or piano playing. We consider this task as an important step towards higher adoption rates of robotic prostheses among arm amputees, as it has the potential to dramatically increase functionality in performing daily tasks. To this end, we present an end-to-end robotic system, which can successfully infer fine finger motions. This is achieved by modeling the hand as a robotic manipulator and using it as an intermediate representation to encode muscles' dynamics from a sequence of US images. We evaluated our method by collecting data from a group of subjects and demonstrating how it can be used to replay music played or text typed. To the best of our knowledge, this is the first study demonstrating these downstream tasks within an end-to-end system.}, author = {Zadok, Dean and Salzman, Oren and Wolf, Alon and Bronstein, Alexander}, booktitle = {2023 IEEE International Conference on Robotics and Automation}, location = {London, United Kingdom}, publisher = {IEEE}, title = {{Towards predicting fine finger motions from ultrasound images via kinematic representation}}, doi = {10.1109/icra48891.2023.10160601}, volume = {27}, year = {2023}, }