arXiv subjects

Alex M. Bronstein

Publications and source records attributed to Alex M. Bronstein.

At least 19 recordsLinked to original sources

arXiv2026

Inducing Fourier Geometry: A Smoothness Prior Imposes Approximate Translation Equivariance in Multimodal Stellar Embeddings

Learned representations often contain geometric structure induced by symmetries in the underlying data. We ask whether a known continuous parameter space can instead be used to \emph{induce} such structure when the corresponding symmetry is only approximate. We introduce a graph-Laplacian smoothness prior that encourages representations to vary smoothly over a physical parameter space without specifying a representation geometry; in the continuum limit it selects Laplacian eigenfunctions and therefore predicts the Fourier-like geometry associated with translation symmetry. On multimodal stellar representations spanning six astronomical surveys, the prior induces Toeplitz Gram structure and sinusoidal modes along stellar parameters, including in modalities whose native representations lack this geometry, while modality-specific residuals preserve structure outside the imposed coordinates. Of the exact-symmetry predictions, stationarity in a recoverable warped coordinate survives; diagnostics assuming exact quantization or asymptotic rates do not. The prior also improves downstream linear-probe performance and label efficiency, suggesting a general strategy: where a meaningful continuous parameter space exists, its local geometry can serve as a data-informed prior.

cs.LG↗

arXiv2026

Fold'EM: Direct atomic structure inference from Cryo-EM particles

Single-particle cryo-electron microscopy (cryo-EM) has become a widely adopted technique for biomolecular structure determination. The conventional cryo-EM computational pipeline first combines many particle images to reconstruct an electrostatic potential (ESP) map and then fits an atomic model to the recovered map. Density reconstruction has high sample complexity, requiring large numbers of particle images and making structure determination high-cost and low-throughput, particularly for heterogeneous samples. Downstream atomic model building, in turn, becomes increasingly difficult as the resolution of the reconstructed map deteriorates. Protein structure prediction models provide strong sequence-derived priors on atomic structure, and experiment-guided approaches can use these priors to recover structures consistent with experimental measurements. Yet, in cryo-EM, such priors are typically integrated only after density reconstruction during atomic model fitting. We introduce Fold'EM, an inference-time framework that combines priors from protein generative models directly with cryo-EM particle images to determine atomic models from a small number of single particle images, bypassing both intermediate density reconstruction and downstream model building against the reconstructed map. Across synthetic and experimental cryo-EM datasets, Fold'EM recovers accurate atomic structures both with known particle orientations and in an ab-initio setting where orientations are inferred jointly with structure. In heterogeneous datasets, Fold'EM further resolves distinct conformational states from mixed particle populations without separately reconstructing a density map and building an atomic model for each state. We believe these results open new avenues for structure determination in the low-sample regime and for characterizing low-population conformational states directly from cryo-EM particles.

q-bio.BM↗

arXiv2026

The Residual Stream's Effective Depth

We introduce \emph{effective depth} ($\Deff$), a scalar diagnostic that treats the layer-wise residual stream of a transformer as a discrete-time process, measures how representation similarity decays with layer distance, and aggregates that profile into one number. Across sixteen decoder-only language models, $\Deff$ separates a structural consequence of residual accumulation from an empirical one: even maximally diverse orthogonal updates have the closed-form reference $F_L = 2L/(L+1)<2$, yet fifteen of sixteen default measurements lie below $F_L$ (Qwen3.5: 32--44\%, OLMo-2: 40--41\%, Pythia: 23--28\%). Matched references show that the gap is not caused by the persistent initial state or update-size imbalance, but is largely a calibrated signature of correlated residual updates rather than evidence that depth is unused. Symmetric position-0, token-normalisation, and top-PC controls show the regime is not reducible to BOS or top-PC artefacts: the lone above-reference default outlier joins the same regime, and all sixteen models are sub-reference after token-normalisation or top-1-PC removal. Intermediate checkpoints show that the regime is established early in OLMo-2 and stable through 5T tokens, while Pythia-1.4B follows a distinct decreasing trajectory. A controlled residual-carry intervention supports the mechanism, and $\Deff$ is best read as a \emph{global} accumulated-state diagnostic, not as a capability score or pruning method.

cs.LG↗

arXiv2026

Invertible Query-Key Coupling Composes with Attention Mechanisms

Scaled dot-product attention forms its queries and keys as independent linear projections, so the two never interact before the dot product that scores them. We study coupled query-key dynamics, a pre-scoring transformation that evolves each token's query and key jointly through a shared invertible coupling before standard scoring. We realize it as an alternating affine map in the style of real non-volume-preserving flows: the coupling is the identity at initialization, adds a small fraction of parameters per head, and leaves the softmax and surrounding architecture unchanged. We place coupling on top of existing attention methods rather than replacing them, and ask whether that composition helps. On WikiText-103, adding coupling to Differential Attention improves on it at both 150M and 455M parameters. At 455M the gain is significant at sequence length 512 (p=0.003, six seeds), survives a Bonferroni correction and replicates on a held-out test split; it also holds across rotary-embedding training lengths 512, 1024, and 2048. The same additive direction appears when coupling is added to query-key normalization (significant at 150M) and Multi-Token Attention (directional). Matched controls attribute the gain to the joint pre-scoring coupling rather than to added capacity, and show that removing the invertibility guarantee preserves the 455M gain yet is far worse than the base method at 150M, so invertibility is what makes the coupling reliable across scales. On its own, coupling lowers perplexity at 60M and 150M (one-sided Welch tests, p<0.05) but the gain narrows with scale and is not significant at 455M. We relate the construction to the expressivity of coupling flows, use an associative-recall study to map where coupling helps and where it degrades sharp retrieval, and conclude that coupling is most useful in composition with a scoring-stage method rather than as a standalone change.

cs.LG↗

arXiv2026

GraphSVR: q-Space--Aware Graph-Based Slice-to-Volume Registration for Diffusion MRI

Diffusion-weighted imaging (DWI) remains highly vulnerable to subject motion, particularly in time-efficient protocols and in motion-prone populations. While slice-to-volume registration (SVR) can mitigate inter-slice and inter-stack misalignment, diffusion MRI introduces additional complexity due to diffusion-direction-dependent contrast and the requirement to align dozens of measurements within a common reference frame, effectively yielding a 4D registration problem. Existing approaches rely primarily on sequential modeling or pairwise similarity and often degrade under sparse gradient sampling or severe motion. We introduce GraphSVR, a q-space-aware graph-based framework for 4D SVR registration in DWI. GraphSVR represents slice groups as nodes in an acquisition-structured graph, with edges encoding temporal proximity, spatial slice geometry and diffusion encoding relationships. A graph neural network predicts globally consistent stack-wise rigid motion, optimized in a self-supervised, zero-shot manner using only an anatomical reference image, without requiring paired ground-truth motion. We evaluate GraphSVR using both fully synthetic diffusion simulations and realistic recombination-based simulations from real acquisitions with controllable motion severity and gradient sparsity. Performance is quantified using grid error (mm) and rotation error relative to known ground-truth transforms. Under severe motion, GraphSVR reduces grid error and rotation error by 73% compared to FSL eddy, the standard DWI motion-correction method, with the largest gains observed in sparse-direction regimes. These results demonstrate that explicitly modeling acquisition structure through graph-based reasoning improves robustness and global consistency in 4D DWI motion estimation. Code is available at https://github.com/nogakertes/GraphSVR.git.

cs.CV↗

arXiv2026

Differentiable Randers-Finsler Eikonal Solvers

Fast and differentiable solvers for anisotropic and asymmetric distance fields are a key primitive in geometry processing, enabling gradient-based optimization over metrics, drift fields, and downstream objectives that depend on geodesic distances and geodesics. We present a differentiable Eikonal solver for Randers-Finsler metrics on Cartesian grids that combines the efficiency of a GPU-friendly column/row fast sweeping with exact gradients obtained by implicit differentiation. Our forward pass uses local one- and two-point upwind updates selected by a causality-valid stencil; the backward pass exploits the induced arrival-time ordering to solve the adjoint system via a single reverse-time back-substitution, avoiding unrolling (i.e., recording and differentiating through every solver iteration) and substantially reducing memory and runtime. We derive closed-form derivatives of the discrete updates with respect to arrival times and Randers parameters, and we enforce metric feasibility with differentiable projections that guarantee positive definiteness and valid drift magnitude. Although stencil selection is piecewise-smooth, we show gradients are stable under small perturbations and match finite differences away from stencil boundaries. We demonstrate accurate forward solutions and enable inverse problems such as recovering spatially varying anisotropic metrics and drift fields from sparse arrival-time supervision. Finally, we apply the method to learning data-driven spread models on real wildfire perimeters, illustrating scalability and the practical utility of differentiable Randers distance fields.

cs.CE↗

arXiv2026

SonoRank: Towards Calibration-Free Real-Time Finger Flexion Detection from Forearm Ultrasound Sequences

Powered prosthetic hands are frequently abandoned, largely due to the limited functionality of current devices that rely on surface electromyography (sEMG). Sonomyography (ultrasound) has emerged as a promising alternative, owing to its ability to observe muscle activity in real time and control a greater number of degrees of freedom. Yet, existing ultrasound-based methods require per-user fine-tuning, limiting their commercialization. We propose SonoRank, an important step towards calibration-free finger flexion detection from forearm ultrasound video. SonoRank first learns to rank pairs of ultrasound sequences by their relative motion magnitude for each of the five fingers. The learned representations are then fine-tuned to classify whether each finger is actively flexing, using a rest reference that is captured at the beginning of the operation. Under 12-fold leave-one-subject-out cross-validation on a dataset of twelve subjects with synchronized kinematics, SonoRank achieves a 28% improvement in F1 score over direct classification baselines that skip the ranking stage. These results establish pairwise ranking as an effective pretraining signal for subject-independent control, bringing ultrasound-based prosthetics closer to practical, calibration-free deployment.

cs.RO↗

arXiv2026

Inference-time optimization for experiment-grounded protein ensemble generation

Protein function relies on dynamic conformational ensembles, yet current generative models like AlphaFold3 often fail to produce ensembles that match experimental data. Recent experiment-guided generators attempt to address this by steering the reverse diffusion process. However, these methods are limited by fixed sampling horizons and sensitivity to initialization, often yielding thermodynamically implausible results. We introduce a general inference-time optimization framework to solve these challenges. First, we optimize over latent representations to maximize ensemble log-likelihood, rather than perturbing structures post hoc. This approach eliminates dependence on diffusion length, removes initialization bias, and easily incorporates external constraints. Second, we present novel sampling schemes for drawing Boltzmann-weighted ensembles. By combining structural priors from AlphaFold3 with force-field-based priors, we sample from their product distribution while balancing experimental likelihoods. Our results show that this framework consistently outperforms state-of-the-art guidance, improving diversity, physical energy, and agreement with data in X-ray crystallography and NMR, often fitting the experimental data better than deposited PDB structures. Finally, inference-time optimization experiments maximizing ipTM scores reveal that perturbing AlphaFold3 embeddings can artificially inflate model confidence. This exposes a vulnerability in current design metrics, whose mitigation could offer a pathway to reduce false discovery rates in binder engineering.

q-bio.BM↗

arXiv2026

Representing local protein environments with machine learning force fields

The local structure of a protein strongly impacts its function and interactions with other molecules. Therefore, a concise, informative representation of a local protein environment is essential for modeling and designing proteins and biomolecular interactions. However, these environments' extensive structural and chemical variability makes them challenging to model, and such representations remain under-explored. In this work, we propose a novel representation for a local protein environment derived from the intermediate features of atomistic foundation models (AFMs). We demonstrate that this embedding effectively captures both local structure (e.g., secondary motifs), and chemical features (e.g., amino-acid identity and protonation state). We further show that the AFM-derived representation space exhibits meaningful structure, enabling the construction of data-driven priors over the distribution of biomolecular environments. Finally, in the context of biomolecular NMR spectroscopy, we demonstrate that the proposed representations enable a first-of-its-kind physics-informed chemical shift predictor that achieves state-of-the-art accuracy. Our results demonstrate the surprising effectiveness of atomistic foundation models and their emergent representations for protein modeling beyond traditional molecular simulations. We believe this will open new lines of work in constructing effective functional representations for protein environments.

q-bio.BM↗

arXiv2026

Effective Sample Size and Generalization Bounds for Temporal Networks

Learning from time series is fundamentally different from learning from i.i.d.\ data: temporal dependence can make long sequences effectively information-poor, yet standard evaluation protocols conflate sequence length with statistical information. We propose a dependence-aware evaluation methodology that controls for effective sample size $N_{\text{eff}}$ rather than raw length $N$, and provide end-to-end generalization guarantees for Temporal Convolutional Networks (TCNs) on $β$-mixing sequences. Our analysis combines a blocking/coupling reduction that extracts $B = Θ(N/\log N)$ approximately independent anchors with an architecture-aware Rademacher bound for $\ell_{2,1}$-norm-controlled convolutional networks, yielding $O(\sqrt{D\log p / B})$ complexity scaling in depth $D$ and kernel size $p$. Empirically, we find that stronger temporal dependence can \emph{reduce} generalization gaps when comparisons control for $N_{\text{eff}}$ - a conclusion that reverses under standard fixed-$N$ evaluation, with observed rates of $N_{\text{eff}}^{-0.9}$ to $N_{\text{eff}}^{-1.2}$ substantially faster than the worst-case $O(N^{-1/2})$ mixing-based prediction. Our results suggest that dependence-aware evaluation should become standard practice in temporal deep learning benchmarks.

cs.LG↗

arXiv2026

DigiArm: An Anthropomorphic 3D-Printed Prosthetic Hand with Enhanced Dexterity for Typing Tasks

Despite recent advancements, existing prosthetic limbs are unable to replicate the dexterity and intuitive control of the human hand. Current control systems for prosthetic hands are often limited to grasping, and commercial prosthetic hands lack the precision needed for dexterous manipulation or applications that require fine finger motions. Thus, there is a critical need for accessible and replicable prosthetic designs that enable individuals to interact with electronic devices and perform precise finger pressing, such as keyboard typing or piano playing, while preserving current prosthetic capabilities. This paper presents a low-cost, lightweight, 3D-printed robotic prosthetic hand, specifically engineered for enhanced dexterity with electronic devices such as a computer keyboard or piano, as well as general object manipulation. The robotic hand features a mechanism to adjust finger abduction/adduction spacing, a 2-D wrist with the inclusion of controlled ulnar/radial deviation optimized for typing, and control of independent finger pressing. We conducted a study to demonstrate how participants can use the robotic hand to perform keyboard typing and piano playing in real time, with different levels of finger and wrist motion. This supports the notion that our proposed design can allow for the execution of key typing motions more effectively than before, aiming to enhance the functionality of prosthetic hands.

cs.RO↗

arXiv2025

Machine-learning inference of stellar properties using integrated photometric and spectroscopic data

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 DESA (Dual Embedding model for Stellar Astrophysics), a novel multi-modal 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 ($R^2 = 0.92$ 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.

astro-ph.SR↗

arXiv2025

Smart Ankleband for Plug-and-Play Hand-Prosthetic Control

Building robotic prostheses requires a sensor-based interface designed to provide the robotic hand with the control required to perform hand gestures. Traditional Electromyography (EMG) based prosthetics and emerging alternatives often face limitations such as muscle-activation limitations, high cost, and complex calibrations. In this paper, we present a low-cost robotic system composed of a smart ankleband for intuitive, calibration-free control of a robotic hand, and a robotic prosthetic hand that executes actions corresponding to leg gestures. The ankleband integrates an Inertial Measurement Unit (IMU) sensor with a lightweight neural network to infer user-intended leg gestures from motion data. Our system represents a significant step towards higher adoption rates of robotic prostheses among arm amputees, as it enables one to operate a prosthetic hand using a low-cost, low-power, and calibration-free solution. To evaluate our work, we collected data from 10 subjects and tested our prototype ankleband with a robotic hand on an individual with an upper-limb amputation. Our results demonstrate that this system empowers users to perform daily tasks more efficiently, requiring few compensatory movements.

cs.RO↗

arXiv2025

Inverse problems with experiment-guided AlphaFold

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 state-of-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 and sometimes better fit experimental data than publicly deposited structures to the Protein Data Bank (PDB). We believe that this approach will unlock building predictive models that fully embrace experimentally observed conformational diversity.

q-bio.BM↗

arXiv2025

Exploring QUIC Dynamics: A Large-Scale Dataset for Encrypted Traffic Analysis

The increasing adoption of the QUIC transport protocol has transformed encrypted web traffic, necessitating new methodologies for network analysis. However, existing datasets lack the scope, metadata, and decryption capabilities required for robust benchmarking in encrypted traffic research. We introduce VisQUIC, a large-scale dataset of 100,000 labeled QUIC traces from over 44,000 websites, collected over four months. Unlike prior datasets, VisQUIC provides SSL keys for controlled decryption, supports multiple QUIC implementations (Chromium QUIC, Facebooks mvfst, Cloudflares quiche), and introduces a novel image-based representation that enables machine learning-driven encrypted traffic analysis. The dataset includes standardized benchmarking tools, ensuring reproducibility. To demonstrate VisQUICs utility, we present a benchmarking task for estimating HTTP/3 responses in encrypted QUIC traffic, achieving 97% accuracy using only observable packet features. By publicly releasing VisQUIC, we provide an open foundation for advancing encrypted traffic analysis, QUIC security research, and network monitoring.

cs.NI↗

arXiv2025

From Lab to Wrist: Bridging Metabolic Monitoring and Consumer Wearables for Heart Rate and Oxygen Consumption Modeling

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 (VO$_{2}$) 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 VO$_{2}$ prediction architecture requiring only the initial second of VO$_{2}$ 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.

cs.LG↗

arXiv2025

WearableMil: An End-to-End Framework for Military Activity Recognition and Performance Monitoring

Musculoskeletal injuries during military training significantly impact readiness, making prevention through activity monitoring crucial. While Human Activity Recognition (HAR) using wearable devices offers promising solutions, it faces challenges in processing continuous data streams and recognizing diverse activities without predefined sessions. This paper introduces an end-to-end framework for preprocessing, analyzing, and recognizing activities from wearable data in military training contexts. Using data from 135 soldiers wearing \textit{Garmin--55} smartwatches over six months with over 15 million minutes. We develop a hierarchical deep learning approach that achieves 93.8% accuracy in temporal splits and 83.8% in cross-user evaluation. Our framework addresses missing data through physiologically-informed methods, reducing unknown sleep states from 40.38% to 3.66%. We demonstrate that while longer time windows (45-60 minutes) improve basic state classification, they present trade-offs in detecting fine-grained activities. Additionally, we introduce an intuitive visualization system that enables real-time comparison of individual performance against group metrics across multiple physiological indicators. This approach to activity recognition and performance monitoring provides military trainers with actionable insights for optimizing training programs and preventing injuries.

cs.LG↗

arXiv2025

Estimating the Number of HTTP/3 Responses in QUIC Using Deep Learning

QUIC, a new and increasingly used transport protocol, enhances TCP by offering improved security, performance, and stream multiplexing. These features, however, also impose challenges for network middle-boxes that need to monitor and analyze web traffic. This paper proposes a novel method to estimate the number of HTTP/3 responses in a given QUIC connection by an observer. This estimation reveals server behavior, client-server interactions, and data transmission efficiency, which is crucial for various applications such as designing a load balancing solution and detecting HTTP/3 flood attacks. The proposed scheme transforms QUIC connection traces into image sequences and uses machine learning (ML) models, guided by a tailored loss function, to predict response counts. Evaluations on more than seven million images-derived from 100,000 traces collected across 44,000 websites over four months-achieve up to 97% accuracy in both known and unknown server settings and 92% accuracy on previously unseen complete QUIC traces.

cs.LG↗