Machine Learning
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Saturday 15 August
Low-rank matrix decompositions can uncover patterns and structure in data and have a number of different applications across many disciplines. Extensions to "joint" low-rank decompositions have been proposed to link datasets from different modalities. While these methods enable the discovery of common patterns across modalities, they require that all the multimodal data share one or more dimensions. We propose a new analysis method, PathFinder, that enables co-analysis of datasets that do not necessarily all share a dimension. The key insight is that as long as pairs or subgroups of matrices do share some dimension, and that there are one or more paths that link across the data matrices, a global joint decomposition can be sought out. This enables the joint estimation of common patterns across different modalities, species, or scales, where a one-to-one mapping across all data along some dimension is not necessarily available. We show that PathFinder is a general umbrella under which many matrix decomposition methods fall as special cases. It can be used to discover common patterns across disparate datasets and to make predictions for missing data or modalities.
Computation and Language
DA-RAC: Distance-Aware Calibration of LLM Judges for Trustworthy AI Auditing
Generative AI systems are increasingly producing real-world artifacts, however their efficacy and validity are often evaluated via context-free LLM-scoring. These judges can be miscalibrated by irrelevant in-context reference examples, creating false confidence and allowing low-quality or harmful outputs to pass evaluation. We study this failure mode as context-induced miscalibration and introduce DA-RAC, a distance-aware reference-anchored calibration method for LLM judges. DA-RAC retrieves semantically and structurally similar labeled anchors for each judgement scenario, weights them by distance, and exposes neighborhood difficulty as a calibration and triage signal. On multi-run LLM-judge evaluation benchmarks, it improves calibration and reduces false-pass risk relative to zero-shot, chain-of-thought evaluation, and static-anchor baselines. Mechanistic analysis shows that judge scores vary systematically with anchor distance, while static references can induce misleading decision boundaries. Thus LLM-judgement requires not only better models, but also calibrated, auditable reference selection, especially when automated evaluation is used to support high-impact AI generated artifacts. Judgments should be grounded in relevant, inspectable, and contestable interpretive artifacts.
Read the full abstract
Human-Computer Interaction
Who's Keeping Score? Interactive Steering of LLM-Powered Scoring with Attune
Large language models (LLMs) are increasingly used to score text records at scale (e.g., rating candidate resumes on a 1-5 scale). However, existing LLM-powered approaches do not account for the fact that effective scoring requires both holistic understanding of records and locally consistent judgments across similar ones. We present Attune, a mixed-initiative system for steerable LLM-powered scoring. Given a task description and scoring range, Attune performs pairwise comparisons across records to develop a global understanding first, and then resolves these comparisons into consistent score assignments-deriving scoring criteria and rules bottom-up in the process. These serve as shared representations of scoring logic that users can inspect and edit. Based on insights from a formative study (n = 12), Attune's interface introduces novel steering interactions that allow users to deterministically refine scoring logic. Users can provide examples, directly edit criteria, rules, or target distributions, and give natural language feedback-with all refinements compiling into constraints that guide re-scoring. We validate our approach through a technical evaluation across three workloads and a user study with domain experts (n = 8) in healthcare, law, education, and AI evaluation.
Read the full abstract
Artificial Intelligence
RETRACE: Resilience-Guided Trait-Conditioned Craving Estimation from Wearable Physiology in Opioid Use Disorder
Detecting opioid craving from wearable physiological signals is critical yet difficult, with the potential to support proactive interventions for individuals with opioid use disorder (OUD). This challenge is especially pronounced under subject-independent evaluation because craving is subjective, heterogeneous, and often physiologically entangled with stress. Our empirical analysis shows that stress elicits strong and reproducible autonomic responses, while craving-related signals are weaker, sparse, and largely embedded within stress-related physiology. We further show that psychological resilience, which shapes stress regulation and craving vulnerability, is not reliably observable from short-term wearable windows, but can be captured through reusable subject-level proxies, including post-stress heart-rate recovery and autobiographical memory recall. Motivated by these findings, we introduce RETRACE, a resilience-guided trait-conditioned framework for subject-independent craving estimation from wearable physiology. RETRACE reframes craving detection as trait-conditioned physiological interpretation: rather than assuming the same physiological pattern has the same meaning across individuals, it uses resilience-related subject context to guide inference. Technically, RETRACE introduces a novel dual-encoder design that separates generalizable stress physiology from subject-specific craving interpretation. It combines a frozen stress-pretrained encoder with resilience-conditioned craving encoder, using feature-level gating and representation-level fusion to enable lightweight personalization without target-user craving labels or per-user retraining. We evaluate RETRACE on a novel multimodal OUD dataset containing wearable physiology, stress and craving annotations, and autobiographical narratives. Under LOSO setup, RETRACE achieves up to 7% absolute improvement over the strongest baseline.
Read the full abstract
Friday 14 August
Computers and Society
New Lenses on Learning Design: Course Types and Indicators from Large-Scale Moodle Data
Although learning design (LD) plays a central role in shaping online courses, large-scale empirical evidence on how courses are actually structured remains scarce, and existing analytics work has characterised courses through student engagement with specific learning activities rather than through indicators of the design itself. This study addresses both gaps through an analysis of learning management system (LMS) data from 606 courses at a distance university. Using LMS data, we first applied dimensionality reduction and clustering to a structural variable set, from which three distinct LD types emerged empirically: Compact, Expansive, and Interactive and statistically characterised how their design elements differ across disciplines, activity load, and interfaces. Building on this typology, we derived three LD indicators, activity-mode balance, structural clarity, and analytics readiness, each combining multiple LMS-derived variables into higher-order constructs that target a different aspect of LD. All three indicators differentiated significantly across the LD types and added pedagogically meaningful dimensions for interpretation. These contributions advance the operationalisation of LD in technology-enhanced learning research by demonstrating that higher-order LD indicators can be derived directly from routinely collected LMS data, and offer empirical insight into how LD manifests at scale within a large distance university.
Read the full abstract
Machine Learning
PolyGraph: Plan-Buffered CUDA Graphs for Adaptive Speculative Decoding
Adaptive speculative decoding changes the active batch size B and draft length d from one decode step to the next, whereas a CUDA Graph replays a fixed launch configuration. The resulting verification width M = B d forces serving systems to pre-capture many shapes, capture new ones on the serving path, or pad every step to the largest draft. We present PolyGraph, a plan-buffer mechanism for custom Triton kernels that avoids this choice. PolyGraph captures one maximum-grid graph and writes the active shape to GPU memory before each replay. Kernels skip tiles beyond that shape, while graph topology, allocations, layouts, pointers, and launch grids remain fixed; the update transfers only 28 bytes. On one NVIDIA H800, a trace-driven prototype with Qwen2.5-3B dimensions replaces 64 shape-specific graphs with one, matches the warmed baseline in observed step latency (17.7 vs. 17.8 ms P50), and reduces measured pre-serving graph-build time from 3,915 to 93 ms. Fixed-draft controls show that the benefit comes from avoiding padded payload: the P99 difference from MaxPad is negligible at zero padding waste but reaches an 18.7% reduction at 100% waste. Our evidence establishes a bounded work-shape mechanism for custom kernels, not a production serving system, and is limited to synthetic traces on one GPU.
Read the full abstract
Sound
RDSE: Real-Time Directional Speech Enhancement Framework for Dual-Mic Commodity Smartphones
Audio-visual zooming on mobile devices is fundamentally constrained by limited microphone count, compute resource, unknown array geometry, and weak assumptions on real-world acoustic conditions. We present RDSE: Real-Time Directional Speech Enhancement Framework, a hybrid pipeline that combines traditional signal processing and modern machine learning methods for dual-microphone low-end smartphones. Unlike tightly coupled AV systems that continuously use visual feeds or embeddings, RDSE decouples visual interaction from feature inference, using camera input solely to parameterize the steering vector for spatial filtering. The proposed system uses four modules: dereverberation network, a beamformer with a temporal convolutional network, and a MetricGAN based denoiser. Extensive evaluation on benchmark data and real-world recordings demonstrates effective zooming without precise geometry calibration. Comparative experiments show competitive performance to existing methods. Proposed system is rigorously tested for statistical validity, ablation study, latency profiling, and practicality through real-time live-streaming.
Read the full abstract
Cryptography and Security
A Throughput-Oriented Analytical Model for Post-Quantum Security Protocols
Growing awareness of the impact of quantum threat on classical cryptography directly translates into a growing demand for accurate network simulation tools capable of estimating the integration effects of quantum-safe cryptography in current systems. In particular, the adoption of Post-Quantum Cryptography (PQC) has a direct impact on the performance of network endpoints and transmission overhead. This also affects the scalability of widely adopted security protocols such as TLS and SSH. In this paper, we present a throughput-oriented analytical model that provides a tight upper bound on the maximum sustainable rate of post-quantum secure connection establishment in TLS and SSH. This model takes into account both endpoint and network capacity constraints, decomposing the handshake process into dominant cryptographic operation time and network transmission time. Identifying the bottleneck allows us to derive the achievable throughput in terms of handshakes per second. The experimental results provided show the accuracy of the model against the data obtained from an experimental testbed using, among others, NIST standard primitives from FIPS 203, 204, and 205, including ML-KEM and ML-DSA. Finally, we integrate our model into a network environment and demonstrate how it can be leveraged to enable efficient resource allocation among multiple endpoints, optimizing PQC traffic in multiple-unicast scenarios.
Read the full abstract
Cryptography and Security
Neural Fingerprints for Malware Analysis: An Image-Based Metric Learning Approach with Application to Cross-Domain Classification
Identifying the family of a newly observed malware sample is a core task in threat intelligence, yet conventional classifiers must be retrained whenever a new family appears. This chapter develops an image-based metric learning approach that instead learns to extract discriminative neural fingerprints–fixed-length embeddings–from malware-as-image representations, so that family membership can be determined by nearest-neighbor search in the embedding space. The central advantage of this formulation is zero-shot capability: because the learned embedding induces a similarity metric rather than a fixed set of class boundaries, families that were never seen during training can be recognized by comparison against a gallery, with no retraining. We demonstrate this directly by training an encoder on MalNet-Images-Tiny and MalImg combined (453 families, 96,769 images) and evaluate it zero-shot on a held-out 17-family grayscale dataset with no family overlap. Using a lightweight CNN with multi-proxy anchor loss, this model attains 73.1% retrieval@1 and 90.5% open-set AUROC on families the encoder has never seen. We benchmark our embedding approach against two conventional paradigms in a same-domain setting, where all three are competitive at classifying malware into families. We further show that the learned embeddings transfer across datasets. Unlike classifiers, our embedding approach also yields interpretable similarity scores and scales to large galleries via Facebook AI Similarity Search (FAISS). Finally, we provide a comprehensive evaluation of the learned embedding space using retrieval@k, cluster purity, silhouette score, separation ratio, few-shot accuracy, and open-set detection metrics, along with robustness analysis under image perturbations.
Read the full abstract
Cryptography and Security
Image-Based Techniques and Ensemble Soft Voting for Malware Classification
In this chapter, we investigate image-based malware family classification using an ensemble learning framework and a soft voting strategy. We consider malware binaries that have been converted into images using eight distinct conversion strategies. Three complementary feature extraction tracks are applied to these images: handcrafted descriptors combining Histogram of Oriented Gradients (HOG) and Haralick texture features along with 38 statistical features; dense embeddings obtained from three pretrained neural networks (VGG16, ResNet50, and ViT-B/16), where each pretrained model is used as a frozen feature extractor with its classification head removed; and 512-dimensional embeddings derived from a custom Convolutional Neural Network (CNN) trained directly on the malware images. Each of the three feature extraction techniques is evaluated with machine learning classifiers across all eight image conversion types. The best individual results are 77.8% accuracy for the handcrafted features, 73.8% for the pretrained neural network track, and 74.8% for the custom CNN track. Then we consider various soft voting ensemble strategies, and we find that the best-performing soft voting pool–consisting of fifteen voters selected on a dedicated validation split–achieves 80.2% accuracy across the 17 malware families under consideration, a statistically significant improvement of 2.4 percentage points over the best individual model. A quantitative diversity analysis confirms that the different feature representations are complementary, with the handcrafted descriptors being the strongest contributors.
Read the full abstract
Machine Learning
On the Effect of Bit-Level Parameter Perturbations in Machine Learning and Deep Learning Models
In this chapter, we investigate how classical machine learning models respond to small, targeted modifications in their parameters. We compare and contrast these results to analogous experiments on deep learning models. For classical learning models, we consider Hidden Markov Models (HMM) and Support Vector Machines (SVM), and for comparison, we conduct analogous experiments involving Multilayer Perceptrons (MLP) and Long Short-Term Memory (LSTM) networks. When applied to the Drebin Android malware dataset, our results show that classical models are brittle, in the sense that a limited set of selected parameters can have a dramatic effect on model behavior. In a related set of experiments, we investigate the steganographic capacity of these same learning models, that is, the proportion of bits in model parameters that can be overwritten without having a significant adverse affect on a model. We find that classical models offer limited steganographic capacity due to their compact, parameter-efficient, and relatively sensitive parameter structure. In contrast, neural networks are parameter-redundant, enabling higher steganographic capacity, where modifications can be distributed across many parameters with minimal impact on performance. These results highlight differences in how classical and neural models respond to parameter changes, with clear implications for both robustness and hidden information embedding. Overall, this work provides a framework for understanding parameter sensitivity and steganographic capacity across different classes of learning models.
Read the full abstract
Artificial Intelligence
FISSION: Label Augmentation for Bot Detection
Bot accounts and coordinated influence operations are often discovered via heuristic methods, leaving a dearth of reliable ground-truth labels for training detection systems. To address this challenge, we study a natural question: can we generate labels to assist in learning embeddings in which bots and accounts from the same coordinated operation are close? We present FISSION, a method to generate labels by splitting each account's activity into positively labeled sub-accounts. Given this label source, we train detection models which preserve behavioral regularities recurring across positive sub-accounts. We evaluate FISSION and show it outperforms prior methods in detecting Wikipedia sockpuppets and Twitter/X bots.
Read the full abstract
Numerical Analysis
Sharp Approximation on the Sphere by Linearized Shallow Networks with Analytic Activations
We study the spectral behavior and approximation properties of linearized shallow networks with analytic activation functions on the unit sphere $\mathbb S^d$. Motivated by earlier spherical approximation results for analytic zonal functions \cite{mhaskar1999approximation}, we first derive an asymptotic formula, expressed explicitly in terms of the residues, for the ultraspherical coefficients of a real-analytic function whose relevant singularities are a conjugate pair of simple poles on the imaginary axis. In particular, the formula gives a matching lower bound along the relevant high-degree subsequences and identifies the exponential decay scale and sign oscillation. It applies directly to $\tanh$, the logistic sigmoid, and the rational activations considered here, while the corresponding estimate for $\arctan$ is obtained through differentiation. For such activation functions and quasi-uniform points $\{\theta_j^\ast\}_{j=1}^n \subset \mathbb S^d$, functions $f \in \mathcal H^r(\mathbb S^d)$ satisfying the appropriate spectral compatibility condition can be approximated by a linear combination $$f_n(\eta) = \sum_{j=1}^n a_j \sigma(\theta_j^\ast \cdot \eta),$$ with the sharp Sobolev rate $$\|f - f_n\|_{\mathcal H^s(\mathbb S^d)} \lesssim n^{-\frac{r-s}{d}} \|f\|_{\mathcal H^r(\mathbb S^d)}.$$ The approximation theorem places the $\mathcal H^s$ norm on the left-hand side and simultaneously provides an explicit normalized $\ell^2$ bound on the coefficients. For spectrally compatible analytic target functions, the same construction further gives the stated analytic convergence rate. Thus, the analysis connects spectral asymptotics and lower bounds at the degrees where the ultraspherical coefficients do not vanish with Sobolev-norm approximation and coefficient control for fixed analytic activation functions.
Read the full abstract
Machine Learning
JAMPR+/L2D: scalable neural heuristic for constrained vehicle routing problems in dynamic environment
The vehicle routing problems with real-world constraints (we consider vehicles capacity limits, time windows constrains, pickup-and-delivery multi-depo — CPDPTW) pose significant computational challenges. While classical exact and heuristic methods remain effective to solve problems of small/medium size ($N\lesssim100$), they often lack adaptability and scalability for larger logistics tasks. In this work, we show how JAMPR+/L2D RL deep learning model, proposed in to solve large CPDPTW problems can be adopted in the case of substantial changes of graph distance matrix. We test performance of JAMPR+/L2D model for medium-sized CVRP and VRPTW problems on CVRPLIB benchmarks: JAMPR+/L2D outperforms the state-of-the-art heuristic HGS in over 85% of instances, achieving improvement in objective gap. We show that the JAMPR+/L2D model trained on CPDPTW problem, generalizes well for tasks with simpler constraints (CVRP, VRPTW), for different problem sizes and for moderate changes in distance matrixes. For more substantial changes in distance matrixes, we propose here to make fast finetuning of JAMPR+: on ORTEC data (for CPDPTW) the proposed strategy remarkably reduces the objective gap without full model retraining, what will give both accuracy and rapid inference of the model in the practical routing scenarios with distance matrix changes.
Read the full abstract
Machine Learning · Cross-listed from math.CT
Sample-Smooth Spaces: A Convenient Category for Differentiable Probabilistic Programming
We introduce the category $\mathbf{SSS}$ of sample-smooth spaces over a mixed site. The test objects are the products $\Omega_n := \mathbb{R}^n \times \Omega$ of a Cartesian space with the universal Hilbert cube $\Omega$ carrying all universally measurable sets, and a space is a set with a family of admissible plots $\Omega_n \to \mathcal{X}$ closed under precomposition. Smoothness and measurability are then not two structures glued along an axiom, but one structure over one site. The site has finite non-empty products, because $\Omega$ absorbs its own square; its Karoubi envelope contains every $\mathbb{R}^n$; and it has mixed morphisms $\omega \mapsto (W(\omega),\Phi(\omega))$, which turn measurability of a smooth family from an axiom into a consequence. $\mathbf{SSS}$ is a concrete quasitopos: complete, cocomplete, cartesian closed and locally cartesian closed, with a classifier for embeddings. Morphisms of Cartesian spaces are exactly the $C^\infty$ maps and manifolds embed full and faithfully, both without Boman's theorem. Every object has tangent and cotangent spaces, every morphism a differential. The modalities sit in an adjoint string $\Pi \dashv \flat \dashv \natural \dashv \sharp \dashv \Lambda$, making $\mathbf{SSS}$ cohesive over quasi-universal spaces. The point is the probability monad. Defining the plots of $\mathsf{P}(\mathcal{X})$ as push-forwards of $\mathcal{X}$-plots at every test object, $\mathsf{P}$ is an unconditional strong commutative affine monad on all of $\mathbf{SSS}$ – functor, unit, product of kernels, multiplication and the monad laws are each one line of seed splitting – and its Kleisli category, of differentiable simulators, is a Markov category. The reparametrisation trick holds by construction: every Kleisli morphism is plot-wise a sampler, stably under composition. A reflection theorem locates the whole gain in a single plot family.
Read the full abstract
Artificial Intelligence
Decoupling Is Not Identification: Supervised Evidential Learning in Next-Token Prediction
A next-token probability says what a model predicts, not how much training support lies behind it. A Dirichlet head can represent this distinction by separating mean $m$ from concentration $S$, but decoupling does not identify what $S$ means. Here we propose an Evidential Next-Token Prediction (ENTOP) framework to audit this gap on character-level Moby-Dick, using exact 8-gram count as a reproducible lexical-support label and withholding count regression from 20% of context types. Standard implicit evidential training carries essentially no count signal beyond confidence on held-out-label types (partial Spearman $\rho = 0.001 \pm 0.014$), whereas explicit supervision generalizes ($\rho = 0.201 \pm 0.010$; matched-pair win $= 0.822 \pm 0.021$). CE predictive entropy is at chance for unseen 8-grams (AUROC $= 0.490 \pm 0.004$), while supervised vacuity reaches $0.772 \pm 0.003$, comparable with an indexed CE-representation baseline ($0.769$) but below the tautological corpus oracle ($1.000$). Neither longest-suffix nor representation-distance strata explain where amortization succeeds. Increasing count weight under the digamma objective improves support fit only by sacrificing prediction. A constant predictor wins natural log-RMSE, and vacuity does not improve error deferral. These results motivate a minimum evidence protocol—confidence control, matched pairs, held-out labels, a constant baseline, and a decision test—and show that concentration can pass identification while failing calibration and utility.
Read the full abstract
Robotics
Multi-Axis Selective Decoupling Framework for Free-Floating Space Manipulators
Free-floating space manipulator systems face operational challenges due to dynamic coupling. While traditional reactionless manipulation eliminates base disturbances, enforcing the null-space projections across all rotational axes imposes excessive constraints on the system and drastically reduces the available workspace. To address this limitation, this work proposes a multi-axis selective decoupling framework that nullifies momentum transfer exclusively along mission-critical directions. By leveraging a directionally constrained sub-coupling matrix, the framework relaxes the null-space constraints. Numerical simulations confirm that this approach mathematically eliminates constrained directional disturbances along the targeted axes while preserving the remaining degrees of freedom, enabling the manipulator to execute task-space operations successfully.
Read the full abstract
Artificial Intelligence
A Multi-Timestep LSTM Ensemble regressor for Enhanced Short-Term Runoff Prediction
Accurately forecasting river runoff is key to managing water resources, controlling floods, and planning agriculture. This study examines the Ajichay River in northwest Iran, a major tributary of Lake Urmia that has experienced increasing water-related stress in recent years. We introduce a daily runoff prediction model based on Long Short-Term Memory (LSTM) networks. The model combines five LSTM units, each trained on different time intervals ranging from 2 to 6 days, to better capture variations in river flow patterns. To improve performance, each model was fine-tuned using Particle Swarm Optimization (PSO), a population-based optimization algorithm. The proposed approach was evaluated on unseen data from 2017-2018 using $R^2$, RMSE, and MSE as performance metrics. The results showed strong predictive accuracy, with $R^2$ values ranging from 74.95% to 91.42%. In addition, multiple feature-importance methods were applied to identify the most influential variables, providing further insight into the factors that drive runoff variations.
Read the full abstract
Machine Learning
Partially Observed Sparse Graphs: The Unknown Sampling Rate is a Tail Index
A large graph is often available only in part: a crawl stopped by its budget, a panel, a partial dump. When the sampled fraction $s$ is known by design the total edge count follows from $\hat e=e_s/s^2$ and no model is needed. We treat the case where $s$ is unknown and the population size is known. Our main result is a reduction: under a sparse exchangeable (graphex) model the expected non-isolated fraction obeys $n_s/n_1\to s^{1+\sigma}$, so the sampling rate becomes estimable once the tail index $\sigma$ is, and substituting it back gives $e_s(n_1/n_s)^{2/(1+\sigma)}$ – the same estimator, with the design quantity inferred. Estimating global edge cardinality in a sparse graph is therefore, in expectation, tail-index estimation, and the quadratic graphon estimator is the case $\sigma=0$: it fails by an identity rather than by a fit ($260\%$ median error against $27\%$). We bound the finite-size error of the substitution and show the reduction is modular in the tail-index estimator — filled with a published closed-form one it reaches $21.7\%$ over $13$ networks and $39$ sampling budgets with no fitting at all. Fitting a full graphex additionally returns the degree distribution at any size and a generative object, in a representation where sparsity is a coordinate and the interpolation path is dictated rather than chosen. Two limits are exact: rank-one graphexes have transitivity fixed by the degree profile, so high-clustering graphs lie outside the class; and under snowball or random-walk crawls every method here fails, the design-based oracle worst of all ($7.8\%$ to $588\%$).
Read the full abstract
Machine Learning
Intervention, Not Shared Latents: Blocking Visual Shortcuts in Audio-Video Generation
Joint audio–video (AV) generators are trained on data in which what an event looks like and what it sounds like are spuriously correlated. We present a controlled causal study of the resulting failure mode. In an AV structural causal model where the audio is, by construction, independent of the video's nuisance appearance, models that let audio read video directly—through cross-attention or a shared latent—learn a visual shortcut: they predict sound from appearance rather than the causal event and, when the appearance–event correlation is broken at test time, synthesize the wrong event's sound. Crucially, the popular remedy of routing both modalities through a shared common-cause latent does not fix this—a bottleneck, an unsupervised shared/private factorization, and a faithful shared-prior model all grab the appearance proxy and fail like the direct model. Blocking the shortcut instead requires an intervention on the nuisance: under the stated assumptions we prove that counterfactual invariance is necessary and sufficient to identify the causal predictor, and we verify the mechanism from feature-vector SCMs to procedural pixel video, real images with spectrogram audio, moving real digits, and a conditional generator. On a real, pretrained V2A generator (MMAudio), an input-intervention test shows the model is far from invariant to sound-irrelevant edits, though a generic-noise control reveals it is broadly input-brittle rather than specifically colour-shortcutting—clean isolation of the shortcut needs the controlled confounds our synthetic studies provide. We characterize when the shortcut occurs, compare the objective against supervised counterfactual augmentation, and isolate the unknown-nuisance regime—where the intervention cannot be applied—as the central open problem.
Read the full abstract
Machine Learning · Cross-listed from eess.SP
Comparative Analysis of State-of-the-Art Foundation Models for Sleep Analysis Under Channel Reduction
Automatic sleep staging from polysomnography (PSG) is a well-studied task, but PSG itself is expensive, clinic-based, and burdensome to manually score, which limits its use for long-term or at-home monitoring. Most existing sleep-staging foundation models are evaluated using the full PSG montage. We instead ask how much of that montage is actually necessary. We evaluate six sleep staging models on the Multi-Ethnic Study of Atherosclerosis (MESA) PSG dataset across three signal conditions: electroencephalography (EEG), electrocardiography (ECG), and their combination (EEG+ECG). This is motivated by edge-cloud deployment, where EEG requires a clinic-grade scalp electrode, whereas ECG is already captured by consumer wearables. We test state-of-the-art foundation models such as SleepFM with an encoder trained from scratch on MESA, alongside BIOT, MOMENT, LaBraM, a base-scale Vision Transformer (ViT-B) reimplementation of SensorLM trained from scratch, and YASA, spanning EEG-pretrained, general-time-series, from-scratch, and classical non-learned approaches. No model architecture is modified from its original form; SensorLM's encoder is reimplemented only in PyTorch. For EEG-only staging, BIOT achieves the best result with a macro~F1 of 0.7237, followed by LaBraM (0.6835) and SleepFM from scratch (0.6582). Across the five models capable of ECG-only staging, switching from EEG to ECG costs between 0.2798 (MOMENT) and 0.4151 (BIOT) macro~F1, averaging 0.3531, while cutting the raw channel data rate to a third. Adding ECG to EEG provides no gain for most models. These results show that EEG carries most of the sleep-staging signal, quantify the consistent accuracy cost of the wearable-compatible alternative, and demonstrate that sleep-relevant pretraining transfers well to MESA.
Read the full abstract
Computation and Language
DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation
As automated scientific discovery advances, Large Language Models (LLMs) can now generate research ideas at an unprecedented scale, shifting the bottleneck from idea generation to idea evaluation. Existing evaluators mainly rely on parametric LLM knowledge or unstructured retrieval, producing judgments that lack the experience-grounded reasoning used by human instructors. To address this, we propose DeepInstructor, an agentic framework that formulates idea evaluation as reasoning over structured scholarly experience. DeepInstructor constructs an Experience Graph from 58,607 peer reviews and employs a ReAct-based agent to retrieve dimension-specific evidence for traceable evaluation. We further introduce DeepInstruct, a dataset with controlled pairwise comparisons across novelty, significance, and feasibility. Experiments show that DeepInstructor substantially outperforms existing baselines, improving Hit@1 and Hit@2 alignment with human judgments by 24.4% and 29.7%, respectively. Our findings suggest that scientific idea evaluation can be grounded in explicit reasoning over structured scholarly experience
Read the full abstract
Data Structures and Algorithms · Cross-listed from quant-ph
Quantum Speedups for Log-Concave Sampling from Local Structure
For a convex function $f \colon \mathbb{R}^d \to \mathbb{R}$, the problem of sampling from a distribution proportional to $e^{-f(x)}$ is called log-concave sampling. In many practical scenarios, the function $f(x)$ turns out to admit a local decomposition $f(x) = \sum_{a=1}^R \psi_a(x_{S_a})$. In this paper, we consider log-concave sampling using local queries, i.e., evaluation and gradient queries to each clause $\psi_a(\cdot)$, which can be computationally much cheaper than the queries to $f(x)$ itself. We show that if each coordinate appears in only a small number of clauses, there is a quantum algorithm for strongly log-concave sampling using $\widetilde{O}(\sqrt{\kappa}d)$ local queries, where $\kappa$ is the condition number. This improves the prior best classical result $\widetilde{O}(\kappa d)$ due to Ascolani, Lavenant, and Zanella (Ann. Probab. 2026) and the quantum result $\widetilde{O}(\sqrt{\kappa} d^2)$ implied by Childs et al. (NeurIPS 2022). Our quantum sampler applies to a broad class of locally structured models from statistical computing and machine learning, with representative examples including Gaussian Markov random fields, finite-element latent Gaussian models, and sparse generalized linear models. These results demonstrate that local structure is not merely an implementation detail, but a quantum algorithmic resource for high-dimensional sampling.
Read the full abstract
Machine Learning
GradRepair-ODE: Certified Gradient Repair for Neural ODE Training
Neural ordinary differential equations use numerical solvers inside the training loop. The solver determines the forward trajectory and also affects the gradient passed to the optimizer. That coupling creates a reliability problem for scientific machine learning and continuous-time generative modeling, including diffusion probability-flow ordinary differential equations and flow-matching models. Under loose step sizes, stiff dynamics, chaotic sensitivity, or event discontinuities, a differentiable ODE pipeline can return a finite gradient whose direction is numerically suspect. We introduce GradRepair-ODE, a reliability framework for checking, repairing, and rejecting ODE gradients at the optimizer step. The method computes several gradient candidates, compares them with directional finite-difference checks and solver diagnostics, diagnoses likely numerical failure modes, repairs selected gradients through path switching or stricter recomputation, and rejects steps whose descent direction cannot be certified. In six synthetic ODE systems, GradRepair-ODE leaves low-risk systems unchanged, repairs Robertson and Lorenz gradients to cosine similarity 1.000 against a strict reference, reduces unsafe accepted steps from 37 to 0, and rejects an event-discontinuous case instead of applying an uncertified update. The paper argues for a simple change in the training contract: an ODE gradient should reach the optimizer with numerical evidence attached.
Read the full abstract
Machine Learning
Scalable partial information decomposition for symptom networks via supervised embeddings
Pairwise relationships among mental-health symptoms are routinely summarised asscalar edge weights, which cannot express whether two symptoms carry overlapping information about a third or information that appears only in combination. Partial information decomposition (PID) addresses this gap but is computationally intractable beyond a few sources. We introduce embedding-based PID (ePID), a scalable pipeline that compresses all nonfocal symptoms into a low-cardinality discrete embedding and computes a tractable two-source PID, yielding source-unique, remainder-unique, redundant, and synergistic components for each ordered source-target pair. We benchmarked 13 candidate embeddings on synthetic Bayesian networks calibrated to PHQ-9 and on 83 real-world datasets across five PID measures. A supervised Agglomerative Conditional Information Bottleneck (ACIB) embedding recovered the reference decomposition most accurately of the 13 embeddings tested, and did so for every PID measure yielding non-negative atoms once four or more symptoms were compressed (synergy recovery r = 0.92). The two instruments then diverged sharply. In PHQ-9 networks (UK Biobank,N = 154,291; Xinxiang student sample, N = 24,292) the surrounding symptom context carried most pairwise dependence through redundant and remainder-unique channels; synergy contributed 6 to 9%, and no directed edge was synergy-dominated in either cohort. In the 28-item Interpersonal Reactivity Index, 45% of source pairs were. The identical pipeline, applied without parameter changes, therefore returned opposite profiles for the two instruments, each consistent with how that instrument was constructed. By separating overlapping from interaction-dependent information, ePID provides a scalable, model-agnostic complement to standard symptom-network methodology to distinguish redundant and synergistic contributions to observed correlations.
Read the full abstract
Machine Learning
Do Tabular Foundation Models Still Need Feature Engineering?
Feature engineering has long been a cornerstone of tabular machine learning. Tabular foundation models (TFMs) are pretrained on a wide range of tabular datasets and applied via in-context learning. Their rise raises a natural question: does manual feature construction still matter as these models become more capable? To answer this, we perform a controlled study across several versions of two major TFM families, testing a wide range of existing feature engineering techniques on benchmark datasets from TabArena. We find a consistent pattern: feature engineering gains are concentrated in earlier model generations and become negligible for the strongest models. These results suggest that stronger TFMs depend less on explicitly engineered input representations. In a complementary experiment, however, adding in-context information from related datasets still improves performance. Our findings indicate a shift in the source of performance gains for stronger TFMs: re-representing existing inputs becomes less effective, while providing additional task-relevant context remains beneficial.
Read the full abstract
Machine Learning
Criticality in Dissimilar Decomposition and Undersampling of Random Datasets with Anomalies
Training datasets for upcoming LLMs would include a significant amount of AI text/image data generated from current LLMs. In such a scenario, it is important to understand how this affects batch decompositions and thereby, the performance of the resultant new LLM. In this paper, we consider AI generated data as anomalies “linked" to main data points and study decomposition and undersampling properties of the overall random dataset. We use redundancy graphs and iteration techniques to obtain bounds for the minimum size of a strongly dissimilar (SD) decomposition and demonstrate a phase transition phenomena, wherein the minimum size is essentially determined by the main data points when the number of anomalies is small and is “taken" over by the anomalies above a certain threshold. We also establish a size criticality result for the strong similarity of a randomly undersampled dataset and illustrate our results with examples involving categorical datasets, whose overall space size is much larger than the size of the dataset.
Read the full abstract
Emerging Technologies
PRISM-UDE: Physics-Regularized Iterative Symbolic Modeling of 3nm FinFETs via Universal Differential Equation
Compact transistor models are the mathematical backbone of circuit simulation. However, at advanced nodes such as 3nm, transport physics becomes too complex for traditional hand-derived equations to capture accurately. Purely data-driven neural surrogates, on the other hand, are numerically unstable inside circuit solvers and offer no physical insight into their own predictions. We introduce PRISM-UDE (Physics-Regularized Iterative Symbolic Modeling via Universal Differential Equations), a framework that embeds a small neural network inside a physics-based transistor model, using the network only to learn the transport behavior that the analytical baseline misses, rather than replacing the physics altogether. Once trained, this neural correction is distilled into a single, interpretable closed-form expression via symbolic regression, making the final model fully analytical and simulator-ready. Applied to a 3nm FinFET benchmark dataset, PRISM-UDE reduces prediction error more than sixfold (70.33% to 11.01%) relative to the standard physics-only baseline. The distilled expression preserves this accuracy almost exactly while eliminating the neural network entirely. We further validate the extracted expression directly inside a SPICE circuit simulator, confirming stable, physically consistent behavior under both static bias sweeps and dynamic switching conditions.
Read the full abstract
Machine Learning
Discovering and Preserving Category Correlation Knowledge via Adaptive Reciprocal Knowledge Distillation
Knowledge distillation aims to improve the performance of lightweight student models by transferring knowledge from larger and more powerful teacher models. However, a substantial size gap between teacher and student models often impedes effective knowledge transfer. Most existing approaches adopt a static, one-way teacher-to-student distillation paradigm, which overlooks the dynamic nature of student learning and fails to provide targeted guidance on hard samples. In this paper, we propose adaptive reciprocal knowledge distillation (AR-KD), a novel method that improves knowledge transfer by simplifying the teacher's output distribution. Specifically, AR-KD performs reciprocal adaptation on the teacher by matching its class correlation matrix to the student's relational representation, which reshapes the teacher's prediction structure to better suit the student's capacity. This relational alignment mitigates the collapse of inter-class dark knowledge caused by overconfident teachers, enabling the student to learn from richer and more compatible supervisory signals. We evaluate AR-KD on CIFAR-100 and ImageNet-1k classification datasets, where it outperforms state-of-the-art knowledge distillation baselines. Specifically, AR-KD improves student performance across homogeneous and heterogeneous setups: up to 7.13% accuracy gain for students, 1.42% to 4.15% higher than vanilla KD on average, and further improvements when integrated with other advanced methods. Our code is available at https://anonymous.4open.science/r/ARKD/.
Read the full abstract
Machine Learning
SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanation
One of the pivotal recent challenges in neural network interpretability is polysemanticity, where a single neuron is activated by multiple, often unrelated concepts, hindering clear functional understanding. Although prior work has explored this phenomenon, existing approaches remain architecture-specific and depend on manual heuristics such as a fixed number of concept clusters ($K$), limiting their generality and scalability–especially for modern Transformer-based models. To address these limitations, we introduce SPICE (Simple Polysemantic Feature Interpretation via Clustering-based Explanation), a generalizable framework for analyzing polysemanticity in deep vision architectures. SPICE avoids architecture-dependent propagation rules, enabling the first systematic comparison of polysemanticity across both CNNs and Transformers, and automatically determines the number of concept clusters per neuron, eliminating reliance on a preset $K$ and supporting scalable analysis for large models. Using SPICE, we conduct a comprehensive investigation into how polysemanticity emerges, varies across depth and architecture, and forms through distinct computational pathways.