Machine Learning · Cross-listed from eess.SP
Wavelet Scattering Transform for Interpretable Schizophrenia Biomarker Discovery and Classification from Resting-State EEG
Md. Taksimul Ahsan Tawhid, Nasif Ahmed Rafe, Alif Tahmid Priyom et al. (+1 more)
Schizophrenia is a debilitating neuropsychiatric disorder characterized by profound cortical network dysregulation, for which objective, clinically translatable
EEG based biomarkers remain underdeveloped. Existing automated classification pipelines rely predominantly on static power spectral density features inherently blind to amplitude modulation dynamics and cross-frequency coupling, phenomena central to schizophrenia pathophysiology, while adopting epoch level cross validation strategies that introduce temporal data leakage, artificially inflate reported performance. This study introduces a mathematically principled diagnostic framework integrating the multi-order Wavelet Scattering Transform(WST), strict Leave One Subject Out (LOSO) cross-validation, and SHAP explainability for simultaneous
EEG classification and biomarker discovery. Hierarchical WST coefficients capturing multi-scale amplitude modulation structure were extracted from resting state multichannel
EEG. Subject-level ANOVA with Benjamini Hochberg false discovery rate correction identified significant biomarkers, with Random Forest and SVM classifiers evaluated under strict LOSO cross validation and subject-level majority voting. Second-order scattering coefficients encoding cross frequency coupling dominated the discriminative biomarker set, with gamma-band features most prevalent, demonstrating that temporal amplitude modulation constitutes the primary electrophysiological signature of schizophrenia. Electrode P3 was identified as the single most discriminative site. Under rigorous subject independent evaluation, the Random Forest achieved 90.48% accuracy (AUC = 0.9339; sensitivity = 95.56%). The proposed WST framework establishes a rigorous, interpretable standard for
EEG-driven psychiatric biomarker discovery that can also be applicable in the detection of schizophrenia subtypes in the future.
Read the full abstract ▾
All authors Md. Taksimul Ahsan Tawhid, Nasif Ahmed Rafe, Alif Tahmid Priyom, K. M. Mustafizur Rahman
Machine Learning · Cross-listed from quant-ph
Routing Anonymity and Identifiability of Noisy Quantum Hardware
Ben Priestley and Mina Doosti
Present-day
quantum computing is cloud-based, where a user submits a
circuit to a service provider's proprietary backend hardware. While providers may wish to hide implementation details, scheduling choices, or even which physical device was used, noisy finite-shot outputs can carry backend-specific fingerprints: information imprinted in the classical output distribution that can reveal the backend identity. So far, such fingerprints have mostly been studied from a benchmarking perspective, with limited
attention to
privacy considerations for users and providers. This work develops the first formal framework for backend identifiability and its
privacy implications. We introduce a backend-identifiability game and use it to formalise routing anonymity as a security notion for
quantum cloud services. We show that backend identifiability is a hypothesis-testing problem and prove that, under passive i.i.d. access to a single backend, routing anonymity decays exponentially at the Chernoff rate. We also establish a utility-anonymity trade-off, imposing fundamental limits on how much backend-specific information can be removed from classical outputs without degrading their usefulness. In addition, we observe that, for noisy
quantum hardware, identifying fingerprints are inherently an intermediate-depth phenomenon, and establish a depth principle using Pauli-transfer-
matrix tools. We complement the theory with experiments on Amazon Braket on AWS, using ion-trap and superconducting
quantum processors. We observe 87-90% classification between superconducting backends and 96-100% classification across physical platforms, and find that identifiability can survive natural forms of post-processing. Overall, these results establish routing anonymity as a distinct security requirement for
quantum cloud computing, and provide a framework for quantifying and controlling the utility-anonymity trade-off.
Read the full abstract ▾
Machine Learning
Advances in Neural Controlled Differential Equations
Benjamin Walker
Many real-world systems evolve continuously, yet most machine learning models interpret time series as discrete sequences. Continuous-time approaches instead treat time series as samples from an underlying input path, a formulation that naturally accommodates irregularly sampled or oversampled data. Among these, Neural Controlled Differential Equations (NCDEs) are a maximally expressive class of models that parametrise a vector field using a neural network and evolve their hidden state by solving a dynamical system driven by the input path. NCDEs typically use a non-linear vector field, so their expressive power and continuous-time flexibility come at the cost of a forward pass that is both computationally expensive and inherently sequential, limiting their scalability and practical applicability. This thesis advances the training and scalability of NCDEs through three complementary contributions. First, building on neural rough differential equations, Log-NCDEs apply the Log-ODE method to efficiently approximate an NCDE's solution during training, improving both computational speed and empirical performance. Second, Linear NCDEs replace the non-linear vector field with a linear one, enabling closed-form solutions and parallel-in-time computation without sacrificing theoretical expressivity. Third, Structured Linear NCDEs use structured linear vector fields to further enhance efficiency while maintaining theoretical expressiveness and empirical performance. Collectively, these methods reduce the time per training step for an NCDE by up to three orders of magnitude while achieving state-of-the-art performance across diverse time series
benchmarks.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Untrusted Content Masking for Web Agents with Security Guarantees
Kristina Nikolić, Egor Zverev, Javier Rando et al. (+3 more)
Defenses that provide security guarantees against
prompt injection attacks rely on strict isolation between trusted instructions and untrusted data. In text-based environments such as tool-use APIs, this separation arises naturally:
agents can reason from interface definitions without ever processing untrusted content. Extending these guarantees to web
agents faces a fundamental challenge: to perceive and interact with their environment, web
agents must first observe the rendered page, which intermingles trusted content with untrusted content. This structural
entanglement removes the trust boundary on which security guarantees depend, undermining provable defenses for web
agents. In this paper, we present Untrusted Content Masking (UCM), a simple and effective approach that restores this boundary in web environments. We leverage a key structural insight: a webpage's Document Object Model (DOM) encodes sufficient information to distinguish trusted from untrusted regions without reading their content. Our framework exploits this by redacting untrusted regions before they reach the
agent and routing interaction through a sandboxed interface with strict privilege separation, thereby enabling
agents to observe and interact with their environment while remaining isolated from
adversarial content. The code is publicly available.
Read the full abstract ▾
All authors Kristina Nikolić, Egor Zverev, Javier Rando, Matthew Jagielski, Edoardo Debenedetti, Florian Tramèr
Machine Learning
Adaptive Inference Batching using Policy Gradients
Ruslan Sharifullin
Inference serving systems must balance throughput and latency under bursty, heterogeneous workloads, yet the industry standard remains static batching policies that require manual tuning and cannot adapt to shifting traffic. We investigate whether reinforcement learning (RL) can learn adaptive batching and routing policies that outperform these heuristics, training REINFORCE and PPO
agents on a discrete-event simulator validated against queuing theory and production traces (Azure Functions, BurstGPT). We formulate the problem as an MDP over queue state, request type and GPU availability, evaluating across standard Poisson traffic, extreme bursts, real-world traces and heterogeneous multi-GPU routing. Our central finding is a clear boundary condition for RL's value in systems problems. In single-GPU settings, a well-tuned static batching policy is already near-optimal under Poisson-like arrivals and RL offers only marginal gains (+0.1% to +1.0%). In multi-GPU heterogeneous routing, however, where fast and slow requests compete for shared resources, the
agent discovers a workload-segregation policy that eliminates Head-of-Line blocking, yielding a 3.5x (348%) improvement over Round-Robin and a 48% improvement over the strongest heuristic baseline (Shortest-Queue), with 60% higher throughput and 25% lower latency while respecting SLA constraints. The policy generalizes to unseen bursty and real-world traffic despite training only on synthetic Poisson arrivals and an
attention-augmented policy network converges roughly 20% faster than an MLP baseline. These results suggest RL's advantage over engineered heuristics concentrates in combinatorial, multi-resource decisions rather than single-resource temporal scheduling, a practical distinction for deciding where learned policies justify their engineering cost in production inference infrastructure.
Read the full abstract ▾
Machine Learning
Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach
Qian Hu, Bin Fan, Yao Xiao et al. (+2 more)
Physics-informed neural networks (PINNs) often face ill-posed optimization, competing losses, and parameter compensation in partial differential equation (PDE) inverse problems. Transfer learning can reuse source-task representations, but direct fine-tuning may induce negative transfer when source and target physics differ, leading to low field error but inaccurate parameter recovery. To address this issue, we propose Target-Guided Selective Reweighting PINN (TGSR-PINN), a target-evidence-driven representation correction method for PINN inverse transfer learning. TGSR-PINN transfers source network weights and biases but initializes target physical parameters independently. After target short adaptation, it scores
neurons using first-order Taylor sensitivity and pre-activation variance on fixed batches. These scores are converted into continuous weak-adaptation signals using a Gaussian mixture model with rank fallback. TGSR-PINN then applies bounded selective soft decay to the corresponding input weight rows and biases without
pruning or resetting them. Experiments on a zero-source high-Péclet inflow-
outflow problem with nonzero Dirichlet data and an
outflow boundary layer, Allen-Cahn to Burgers cross-PDE transfer, and 5%-noise reaction-
diffusion inverse problems show that TGSR-PINN improves parameter recovery while maintaining low field error. Ablation studies indicate that
neuron target scoring, weak-adaptation estimation, layer protection, and selective soft decay jointly contribute to the observed benefits.
Read the full abstract ▾
All authors Qian Hu, Bin Fan, Yao Xiao, Zhicheng Lin, Meixin Xiong
Machine Learning · Cross-listed from cs.CV
Is the Geometry Doing the Work? An Operating-Point Audit of Hierarchy in Hyperbolic Vision-Language Models
Jaeyoung Kim, EunSeok Kim and Dongsuk Jang
Hyperbolic vision-
language models are designed to encode abstraction geometrically: general concepts near the origin, specific ones farther out, and entailment cones representing directed order. We ask whether trained MERU, HyCoCLIP, and PHyCLIP models actually use these mechanisms. We audit seven released checkpoints and matched from-scratch interventions. All audited converged checkpoints remain near-Euclidean in the dimensionless radius $u=\sqrt{c}\rho$: the largest observed image-side value is $0.37$ – well below $u\approx0.84$, where local metric distortion reaches $10\%$. Releasing the
curvature floor changes
curvature and norms but not this regime, with mixed, generally modest downstream shifts. Trained entailment cones are saturated or nearly saturated, so low violation rates can arise from trivially wide cones rather than learned order. Preregistered semantic traversal detects weak within-branch order but no operative full-hierarchy readout. Shuffle-controlled tests detect no pair-specific radial ordering in released checkpoints, and no positive result is consistent across all three matched ViT-B seeds. This non-detection is sensitivity-bounded: the diagnostic reaches $80\%$ power only at $\approx13.5$ pp of shuffle-controlled excess, while the largest released gap is $\approx5$ pp. We trace this to a low-
curvature shortcut: lowering
curvature widens entailment cones and suppresses violations without learning order. In the probed trajectories, gradient decomposition identifies entailment as the dominant
curvature-lowering pressure during collapse. Yet
curvature contracts even when entailment is removed, so the shortcut is not the sole cause. Under our diagnostics, the audited formulations do not demonstrate an operative radial or cone-based hierarchy. We distill the audit into a five-number geometry report for evaluating future hierarchy claims.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
SalAngaBhava: A Sinhala Market Dataset for Aspect-based Sentiment Analysis
Lakshani Galwatta, Nisansa de Silva, Sarangi Aththanayake et al. (+1 more)
Sentiment analysis has been a primary domain under Natural
Language Processing (NLP) from its inception as it plays a vital role in both real-world and research applications. In high-resource
languages, this has been extended a step further, and instead of predicting sentiment at the sentence level, models have been developed to detect more fine-grained sentiments at aspect level. However, in order to conduct this fine-grained Aspect-based Sentiment Analysis (ABSA),
datasets annotated with aspects and sentiments toward the said aspects is required. Such
datasets are lacking for low-resources
languages among which, we can count Sinhala, an Indo-Aryan
languages used primarily in Sri Lanka. In this work, we introduce, SalAngaBhava, a new Sinhala Aspect-based Sentiment Analysis
dataset which contains Sinhala product reviews that are manually labeled with aspect terms and the associated sentiments (positive, negative, neutral). The data was collected from domain-relevant sources such as user-generated reviews and comments, and was annotated following carefully defined guidelines to ensure consistency and quality. The
dataset consists of sentences and aspect-sentiment pairs, encompassing a considerable range of aspects from several domains. The analysis confirms that the
dataset is well-structured and sufficiently balanced for ABSA research. This
dataset can be used as a
benchmark and facilitates further studies related to Sinhala natural
language processing, and low-resource sentiment analysis tasks.
Read the full abstract ▾
All authors Lakshani Galwatta, Nisansa de Silva, Sarangi Aththanayake, Adithya Galwatta
Machine Learning
GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation
Zherui Huang, Guanjie Zheng, Hao Xue et al. (+1 more)
Origin-destination (OD) flow modeling underpins urban planning and mobility analysis, but prevailing graph-based methods often neglect salient geographic attributes, limiting their ability to model long-range and multi-area dependencies. In this paper, we introduce GeoFlow, a novel framework that (i) augments area representations with geospatial attributes, including relative positions, k-hop and geodesic distances, (ii) employs a specialized
geometric-intrinsic fusion encoder design that combines graph
attention for intrinsic area signals with coordinate-aware encoders for global structure, and (iii) adopts an axial-global
attention decoder to capture OD-specific competitive dependencies. For OD flow generation, GeoFlow is paired with flow matching models to produce more authentic and diverse mobility samples. Empirically, GeoFlow achieves superior performance in predictive accuracy, while substantially improving generative fidelity and diversity. Ablation and analytical studies confirm the contribution of each component. Code is available at https://github.com/ZheruiHuang/GeoFlow.
Read the full abstract ▾
All authors Zherui Huang, Guanjie Zheng, Hao Xue, Linghe Kong
Machine Learning
FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior Estimation
Weichen Qin, Yufan Xie, Peihao Wang et al. (+8 more)
Simulation-Based Inference (SBI) is critical for scientific discovery, with generative models offering a promising path toward efficient inference. However, existing methods struggle with effective
multimodal modeling. They often rely on brute-force fusion strategies that ignore the structural disparities between parameters and observations, thus limiting estimation fidelity. In this work, we introduce FUSE (Feynman-Kac steered mUlti-modal flow matching for efficient Simulation-based posterior Estimation). Unlike prior work, FUSE employs a dual-track architecture that preserves the distinct features of
multimodal inputs while facilitating dynamic interaction. Additionally, we propose an FK-steered sampling strategy that leverages intermediate observation likelihoods to guide the generative trajectories, effectively improving the sample quality during inference. Our approach outperforms state-of-the-art baselines on standard SBI
benchmarks, producing posteriors that closely match ground-truth MCMC. Furthermore, in a real-world
exoplanet orbital estimation task, FUSE successfully resolves complex parameter degeneracies that challenge existing methods, highlighting its potential to accelerate complex scientific discoveries in astrophysics and beyond.
Read the full abstract ▾
All authors Weichen Qin, Yufan Xie, Peihao Wang, Chia-Jui Chou, Minghui Du, Peng Xu, Ziren Luo, Yi Yang, Jingyi Yu, Bo Liang, Jiakai Zhang
Machine Learning · Cross-listed from cs.CR
Privacy-Preserving Robustness Verification for Neural Networks
Nianyun Song, Xiaokun Luan, Yu Guo et al. (+3 more)
Neural network verification and data
privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by
privacy regulations and intellectual property constraints. This tension has left robustness verification impractical in
privacy-sensitive domains. In this work, we address this gap with SecureCROWN, the first framework for
privacy-preserving neural network robustness verification. Built upon secure two-party computation (2PC), our framework enables a model owner and a data owner to jointly compute certified robustness bounds – revealing only the final result while provably protecting both parties' private data under the semi-honest security model. A key challenge is securely computing the conditional operations in Linear Bound Propagation, where the data-dependent branching is incompatible with standard secure computation protocols. We eliminate branching by formulating conditional logic as continuous arithmetic operations. Additionally, we introduce a Newton–Raphson refinement method to improve numerical stability. Extensive analysis and experiments show that SecureCROWN strictly matches plaintext verification results, while completing in 0.1–200s across varied model sizes and communication settings (LAN/WAN), demonstrating the feasibility of
privacy-preserving neural network verification.
Read the full abstract ▾
All authors Nianyun Song, Xiaokun Luan, Yu Guo, Rongfang Bie, Meng Sun, Xiyue Zhang
Machine Learning
CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling
Zuwang He, Shihao Shu, Yuli Qu et al. (+8 more)
Personalized incentive allocation is vital for e-commerce, where uplift modeling is the standard for estimating Individual Treatment Effects (ITE). However, traditional models often fail in complex multi-seller environments with violations of the Stable Unit Treatment Value Assumption (SUTVA). We identify two critical challenges: Seller-level Cannibalization, where incentives shift expenditure between shops without growing the platform, and Incentive-level Cannibalization, where organic conversions or alternative rewards introduce significant noise into incrementality estimation. In this paper, we propose CanniUplift, a unified framework to mitigate these dual-source cannibalization effects. Specifically, we design Platform-level Global
Alignment (PGA) to capture cross-shop substitution through global GMV consistency constraints. To tackle incentive-driven noise, we introduce Redemption-based Decomposition Denoising (RDD), which uses redemption behavior to decompose treated outcomes and reduce attribution noise within an entire-space framework. Furthermore, a Treat-
Attention mechanism is designed to model intricate interactions between users' historical behaviors and current treatment options. Extensive experiments on both synthetic and large-scale industrial
datasets demonstrate that CanniUplift significantly outperforms state-of-the-art baselines. Ablation studies confirm that the integration of PGA and RDD consistently improves wAUUC and wQINI. Successfully deployed online, our framework achieved a 4.08% relative increase in platform-wide incremental GMV (Delta GMV) over the production baseline and improved ROI in online A/B tests, proving effective in driving global platform growth.
Read the full abstract ▾
All authors Zuwang He, Shihao Shu, Yuli Qu, Hanyu Gao, Ziliang Zhang, Diwei Chen, Xiangda Yan, Buyu Gao, Tanchao Zhu, Yumeng Li, Junxiong Zhu
Machine Learning · Cross-listed from cs.ET
Optimizing ML Workload Partitioning between CPUs and CIM Accelerators for Heterogeneous Computing
Joel Klein, Rebecca Pelke, Roberto Laudani et al. (+2 more)
Computing-in-
Memory (CIM) accelerators execute
Matrix-Vector Multiplications (MVMs) in
memory, making them a compelling solution for Machine Learning (ML) workloads. However, existing ML workload partitioning approaches for CIM accelerators do not fully account for Resistive Random Access
Memory (RRAM) constraints such as limited
memory, high write latency, and limited endurance. They also neglect parallelism, low-level architectural effects, or the Central Processing Unit (CPU) as a complementary compute resource. To address these limitations, we propose an Integer Linear Programming (ILP)-based workload partitioning framework for heterogeneous CPU-CIM systems. It minimizes end-to-end inference latency under RRAM constraints, captures parallelism, and combines empirical profiling with analytical models. Using our framework, heterogeneous CPU-CIM execution achieves speedups of up to 30.9x over CPU-only execution on an edge CPU and 7.3x over a high-performance CPU. A Design Space Exploration (DSE) yields further design insights for future CIM accelerators.
Read the full abstract ▾
All authors Joel Klein, Rebecca Pelke, Roberto Laudani, Jan Moritz Joseph, Rainer Leupers
Machine Learning
Video-based detection of cessation of breathing in pre-term infants using machine learning
Dineo Serame, Lionel Tarassenko and Mauricio Villarroel
Pre-term infants are susceptible to potentially harmful apnoea-related cessations of breathing due to immature respiratory control. However, reliable respiratory monitoring in the neonatal intensive care unit (NICU) remains challenging because motion artefacts, sensor displacement, and skin fragility can compromise contact-based measurements. Non-contact
video monitoring offers a complementary approach that does not depend on adhesive sensors while providing additional respiratory information. We investigated whether camera-based signals can detect apnoea-related cessation of breathing (COBE) and provide complementary information to routinely acquired physiological signals. Using
video and clinical recordings from 30 pre-term infants, respiratory motion was extracted from dynamically tracked torso regions to generate camera-derived time-series signals. Camera-only models were trained using residual network (ResNet) architectures, while hybrid models combined
video-derived signals with impedance pneumography (IP), ECG-derived respiration (EDR), and the PPG-derived respiratory envelope. Camera-only models achieved a balanced accuracy of 76.9%, demonstrating the feasibility of non-contact COBE detection. Combining
video-derived features with IP improved balanced accuracy to 90.6%, outperforming either modality alone and indicating that
video provides respiratory information beyond standard physiological signals. These findings show that
video-derived signals contain clinically relevant respiratory features and enhance COBE detection when combined with conventional physiological signals. This supports non-contact
video as a complementary modality for automated COBE detection and highlights its potential to improve the robustness of neonatal respiratory monitoring.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
msPCA: An R Package for Sparse PCA with Multiple Components
Ryan Cory-Wright and Jean Pauphilet
We present msPCA: an open-source R package for sparse principal component analysis with multiple components. It implements an alternating maximization
algorithm to generate a set of sparse loading vectors that collectively explain a large fraction of the variance in a
dataset, while remaining non-redundant. The
algorithm supports two definitions of non-redundancy: either orthogonality of the loading vectors or zero pairwise correlation between principal components (PCs). In the reported
benchmarks, msPCA solves sparse PCA problems with thousands of features, achieving competitive runtimes while producing sparse components with controlled feasibility violations and a high fraction of variance explained.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Probing Geospatial SSL Representations with Environmental Signals
Rohita Mocharla and Vishal M. Patel
Self-supervised learning (SSL) is designed to learn generic, transferable representations rather than representations optimized for a single task. Most geospatial
benchmarks evaluate representations solely through downstream tasks, providing limited insight into the information encoded within the representation itself. We ask a different question: do SSL representations of satellite imagery preserve statistical associations with environmental variables that co-vary with the imaging process? To answer this question, we probe SSL representations using co-located ERA5 reanalysis variables, a global
dataset of physically consistent environmental variables, including temperature, precipitation, surface
solar radiation, surface pressure, and volumetric soil water. These variables are physically related to the spectral reflectance and radar backscatter recorded by Sentinel-1 and Sentinel-2, making them meaningful evaluation targets despite not being used during SSL pretraining. We complement this probing analysis with intrinsic representation metrics to characterize representation geometry and investigate how these properties relate to downstream performance and the encoding of environmental signals. Using DINO, MAE, and MoCo models trained under identical conditions, we show that representation-level metrics distinguish models with similar downstream
benchmark performance, providing complementary information beyond task-driven
benchmarks. We further find that the linear accessibility of environmental signals is associated with performance on environmentally dependent tasks in the PANGAEA
benchmark. Finally, we release ERA5 annotations co-located with the SSL4EO
dataset to enable physically grounded representation evaluation for future geospatial foundation models.
Read the full abstract ▾
Machine Learning
FlatManifold: Robust Continual Learning under Severe Label Noise and Domain Shifts via Intrinsic Manifold Flattening
Rai Hisada and Kanji Tanaka
In non-stationary streaming environments, simultaneously adapting to complex, non-linear domain shifts via continual learning while mitigating the catastrophic effects of severe, uncalibrated label noise poses a fundamental mathematical challenge. In this paper, we propose \FlatManifold{}, a novel, streamlined robust continual learning framework that utilizes a Nyström
manifold flattening map based on the kernel trick and projection onto an orthogonalized Reproducing Kernel
Hilbert Space (RKHS). Unlike traditional methods that rely on complex, error-prone sample-filtering pipelines, the proposed approach exploits the intrinsic mathematical robustness of the flattened space itself. By mapping feature distributions onto a fixed orthogonal target
topology with a ridge regularizer, the framework naturally smoothes and counteracts the influence of extreme label noise during the optimization process. Concurrently, catastrophic forgetting is prevented via a continual
topology brake term that leverages the covariance
matrix of past experiences. Extensive evaluation on real-world multi-session robotics
datasets demonstrates that even under severe conditions featuring 40% symmetric label noise, \FlatManifold{} successfully mitigates gradient corruption. Under extreme cross-session domain shifts spanning various seasons and lighting conditions, the proposed framework establishes high generalization capabilities, significantly outperforming standard sequential optimization baselines and proving that structural linearization itself serves as a powerful mathematical barrier against distributed label corruption.
Read the full abstract ▾
Machine Learning
Noisy-Channel Minimum Bayes Risk Decoding
Yusuke Sakai, Hidetaka Kamigaito and Taro Watanabe
Minimum Bayes Risk (MBR) decoding yields more robust and higher-quality text generation than maximum a posteriori (MAP) decoding by selecting hypotheses that maximize expected utility over sampled pseudo-references. However, there exists a discrepancy in the design: hypothesis selection calculates expected utility scores conditioned on given pseudo-references, while commonly used evaluation metrics, e.g., BLEU and COMET, are asymmetric. Therefore, it is important to consider both hypothesis-to-reference and reference-to-hypothesis directional effects. In this study, we introduce a noisy channel decomposition of MBR decoding that naturally incorporates bidirectional effects to account for these asymmetries. We decompose MBR decoding into four interacting components: hypothesis-to-reference likelihood, reference-to-hypothesis likelihood, hypothesis prior, and reference prior. This decomposition provides a unified interpretation of existing MBR variants and enables metric- and task-specific interpretability by isolating the contribution of each channel. Our comprehensive analysis reveals that channel-wise contributions exhibit distinct characteristics across metrics while remaining consistent across tasks, and suggests that appropriate channel weighting may lead to improvements over original MBR decoding.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Unified Audio Intelligence Without Regressing on Text Intelligence
Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim et al. (+17 more)
Audio intelligence involves understanding,
reasoning about, and generating both audio and
speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM. Audex adopts a simple unified design with a single
Transformer decoder: audio inputs are encoded and projected into the text
embedding space, while text
tokens and quantized audio output
tokens are treated uniformly during generation. This architecture enables strong audio-text fusion, seamless
multimodal generation, and compatibility with standard LLM training and inference infrastructure. For training, we meticulously curate audio-text
datasets comprising 157.4B audio
tokens and 320.5B text
tokens. We apply multi-stage supervised training on these
datasets, followed by text-only Cascade RL and multi-domain on-policy
distillation. Audex delivers state-of-the-art audio understanding,
speech recognition and translation, text-to-
speech, audio generation, and
speech-to-
speech generation, while preserving very compelling
reasoning,
alignment, knowledge, long-context, and agentic capabilities of its text-only LLM backbone with marginal or no regression. We release the model checkpoints to facilitate open research.
Read the full abstract ▾
All authors Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim, Boxin Wang, Zihan Liu, Sungwon Kim, Yang Chen, Arushi Goel, Rajarshi Roy, Wenliang Dai, Zhuolin Yang, Yangyi Chen, Dongfu Jiang, Sreyan Ghosh, Tuomas Rintamaki, Andrew Tao, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping
Machine Learning
Latent Programming Horizons in Coding Agents
André Silva, Han Tu and Martin Monperrus
A coding
agent solving a software-engineering task spends dozens of steps
reasoning, editing code, and running tests, yet little is known about what the underlying
language model internally represents about the program it is working on. We show that the residual streams of
language models under coding
agents linearly encode properties of the evolving program: a logistic-regression probe on hidden states is able to decode whether the current code parses, passes its test suite, reduces the number of failing tests, and introduces regressions, reaching AUC up to 0.83 for correctness across two models and two
benchmarks. Our second finding is more surprising: these representations run ahead of the
agent's own edits. Probes trained to predict the outcome of future edits (before they are materialized and written on disk) achieve performance above chance up to roughly 25 steps in advance. We call this the
agent's latent programming horizon. As a proof of external validity, we show that the probes transfer across
benchmarks without retraining. Our positive results open calls for more research in mechanistic interpretability of coding
agents.
Read the full abstract ▾
Machine Learning
SMART: A Machine Learning and Monte Carlo Framework for Rapid Analysis of Stochastic Transistor Aging and Process Variation in Digital Circuits
Arash Esshaghi, Siavash Es'haghi, Gholamreza Shahabadi et al. (+1 more)
As CMOS technology scales into the deep nanometer regime, digital
circuit reliability is increasingly threatened by the combined
stochastic effects of Bias Temperature Instability (BTI) and Process Variation (PV). Traditional reliability analysis methods, which rely on computationally intensive simulations or extensive lookup tables, fail to scale efficiently for large designs, creating a critical bottleneck in design space exploration. To address this, we propose SMART, a novel framework that integrates Machine Learning (ML) with Monte Carlo simulation to enable rapid, high-fidelity reliability analysis. SMART employs Random Forest regression to predict gate delay distributions directly, bypassing time-consuming atomic model parameter extractions. Crucially, the model utilizes
Bayesian Optimization for automated hyperparameter tuning, ensuring maximum predictive robustness across diverse libraries. Experimental validation on ISCAS85
benchmark circuits demonstrates that SMART achieves a 94.54% reduction in analysis time compared to state-of-the-art methods, while maintaining a remarkable average accuracy error of just 1.63%. By shifting computational complexity to an offline training phase, the proposed framework offers a scalable, accurate solution for designing resilient, reliability-aware digital systems.
Read the full abstract ▾
All authors Arash Esshaghi, Siavash Es'haghi, Gholamreza Shahabadi, Alireza Moradi
Machine Learning · Cross-listed from cs.AI
Rethinking On-Policy Self-Distillation for Thinking Models
Simran Kaur, Narutatsu Ri, Yinghui He et al. (+2 more)
Self-
distillation is a promising recipe for self-improvement in
language models. In this setting, a model can serve as its own teacher when given privileged information, such as a solution to a math problem. This seems especially appealing for thinking models, which can use test-time
reasoning to absorb the privileged information. Surprisingly, we show that privileged self-
distillation degrades thinking models on long
reasoning traces: across five Qwen3 and OLMo thinking models evaluated on AIME24, AIME25, and HMMT25, privileged-context
distillation causes a relative drop of up to 17% in avg@16 accuracy. The degradation scales with the amount of privileged context withheld from the student and is most pronounced at long rollout budgets, where thinking models otherwise obtain their largest gains. This failure mode is not specific to self-
distillation: on-policy
distillation (OPD) improves thinking models, but privileged OPD reverses these gains. Our diagnostics link this failure mode to how privileged teacher context reshapes learning at high-
entropy forking positions, where multiple continuations remain plausible and may lead to different
reasoning paths. Privileged context lowers fork rates in thinking-model rollouts but not in instruction-model rollouts. This leads to an interesting dichotomy, where privileged context can help instruction-tuned models but hurts stronger thinking models. The effect is visible when the student begins a self-correction branch, where privileged OPD penalizes sampled reconsideration
tokens that vanilla OPD supports. Thinking models trained with a privileged teacher produce fewer verification, backtracking, and hedging markers, even after length normalization. These findings indicate that self-
distillation for strong thinking models requires
attention to
token-level signal, especially around correction and
reasoning steps.
Read the full abstract ▾
All authors Simran Kaur, Narutatsu Ri, Yinghui He, Liam Fowl, Sanjeev Arora
Machine Learning
Relational Multi-Agent Reinforcement Learning for Dynamic Pricing in High-Speed Railway Markets
Enrique Adrian Villarrubia-Martin, David Muñoz-Valero, Luis Rodriguez-Benitez et al. (+2 more)
In liberalised railway systems, operators must set prices dynamically in an environment with partial observability, as they retain private information about their objectives and performance, where regulatory constraints prohibit communication or direct information exchange between competitors to prevent explicit collusion. Consequently,
agents must learn to infer strategic interactions only from observable
market data which presents a significant challenge for multi-
agent reinforcement learning, where standard approaches typically treat observations as unstructured vectors, ignoring the underlying
market topology that governs strategic interactions. To address this, an entity graph modelling approach is proposed, which represents the environment as a graph of operational units, rather than decision-making
agents or static infrastructure, encoding competition, coordination, and connectivity relations between entities. Then, an extension of the multi-
agent twin delayed deep deterministic policy gradient
algorithm with graph-based representation learning processes the features of the entities through a multi-layer relational graph convolutional network and aggregates them via a learnt
attention mechanism. Experimental results in a rail pricing reinforcement learning environment show that this novel framework achieves higher revenue and stability in two different settings of increasing
market complexity compared to a representative selection of relational and non-relational baselines. The code is publicly available at: https://github.com/Kinrre/RelationalRailPricing-RL
Read the full abstract ▾
All authors Enrique Adrian Villarrubia-Martin, David Muñoz-Valero, Luis Rodriguez-Benitez, Giovanni Montana, Luis Jimenez-Linares
Machine Learning
Platonic Projection Structures: Operator-Induced Observability in Representation Learning
Kazuo Ishii, Bishnu Prasad Gautam, Jieling Wu et al. (+1 more)
We characterize observability in representation learning through Platonic Projection Structures (PPS), an operator-theoretic framework for analyzing representation accessibility under partial observation. Rather than treating observable outputs as direct reflections of latent representations, PPS models observation through a self-adjoint positive semidefinite operator acting on a latent representation space. A system is represented as a triple $(H, \Pi, O)$, where $H$ is a latent representation space, $\Pi \succeq 0$ is an observation operator, and $O(v)=\langle v,\Pi v\rangle$ defines an induced scalar observable. Observability is characterized by the quotient geometry $H/\ker(\Pi)$, representing equivalence classes of latent states indistinguishable under observation. We show that
quantum measurement and representation inference under linear observation models share this operator-theoretic structure while differing in the algebraic properties of their observation operators; the correspondence is structural rather than physical. Representation transfer and knowledge
distillation can likewise be interpreted as approximate preservation of observable geometry through $\Phi \Pi_T \approx \Pi_S \Phi$. PPS also reveals a structural limitation of output-based interpretability: latent components in $\ker(\Pi)$ are inaccessible from induced observables, imposing intrinsic constraints on attribution and explanation methods. Controlled empirical validations demonstrate kernel-invariant observability, projection-induced attribution gaps, and rank-controlled observable geometry in latent representation spaces. PPS thus provides an explicit characterization of observability through operator-induced quotient geometry and a unified perspective on representation accessibility, interpretability, and projection-mediated inference.
Read the full abstract ▾
All authors Kazuo Ishii, Bishnu Prasad Gautam, Jieling Wu, Saher Javaid
Machine Learning
MeGA-MP: Metric Graph Advection Message Passing – A Physics-Informed Message Passing Operator for Advection-Dominated Metric Graphs
Janine Strotherm, Luca Hermes, André Artelt et al. (+1 more)
Many real-world systems are organized as networks where spatio-temporal dynamics unfold along connections and not discretely between nodes. Examples include utility networks such as water distribution systems or gas networks, electrical grids, and traffic flow networks. Such systems are naturally modeled as metric graphs, where edges correspond to one-dimensional Euclidean subspaces connected at vertices. Metric graphs are independent of an underlying global Euclidean space, limiting direct application of typical PINNs and operator-learning methods. Especially transport dynamics like advection require a methodology able to capture antisymmetric and long-range dependencies on graphs, which is itself a challenge. We propose a novel physics-informed message passing operator that encodes linear advection on metric graphs as an inductive bias. In the purely advective setting, the operator provably recovers the exact dynamics up to a theoretically derived discretization error without any training. Combined with trainable components like MLPs, our message passing operator extends to realistic advection-reaction dynamics in water distribution systems, where we achieve superior performance compared to baselines and zero-shot generalization across different graph
topologies.
Read the full abstract ▾
All authors Janine Strotherm, Luca Hermes, André Artelt, Barbara Hammer
Machine Learning
Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech
Benjamin Ballyk, Teyun Kwon, Miran Özdogan et al. (+1 more)
Non-invasive
brain-to-
speech decoding aims to restore communication to patients suffering from neurodegenerative disease, without the risks of neurosurgery. Existing MEG- and
EEG-based methods, while scalable, continue to suffer from high word error rates driven by relatively low signal-to-noise ratios compared to invasive recordings. We propose physiological noise augmentation (PNA), a data augmentation method that explicitly trains decoders to become invariant to task-agnostic artifacts (e.g. ocular and cardiac activity). PNA draws inspiration from automatic
speech recognition systems, where environmental noise (e.g. dogs barking, city traffic) is added to clean
speech to improve robustness. Analogously, we decompose
brain recordings into clean data and noise artifacts using independent component analysis (ICA), before scaling and remixing to generate biophysically realistic, label-preserving training examples. We show that PNA approximates anisotropic regularization, penalizing decoder sensitivity along artifact-dominated directions. On MegNIST, a 12k-trial imagined-digit MEG
dataset, PNA with 10-trial averaging improves EEGNet decoding accuracy by 4.7 percentage points (absolute) over training on real data alone. Our results suggest that artifact-aware augmentation and trial averaging are complementary tools for improving robustness in non-invasive
speech BCIs.
Read the full abstract ▾
All authors Benjamin Ballyk, Teyun Kwon, Miran Özdogan, Oiwi Parker Jones
Machine Learning · Cross-listed from cs.CL
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Deyao Zhu, Xin Zhou, Shengling Qin et al. (+44 more)
Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less understood. Analyzing roughly 38,000 hours of
agent interaction with the environment across 134 real world tasks, we find, to the best of our knowledge, the first evidence that overall performance during environment learning follows a log-sigmoid scaling law with remarkably high precision, reaching R^2 = 0.998. Across model generations, we also find that
agent learning speed roughly doubles every three months. This discovery stems from EdgeBench, a suite of 134 real world tasks with ultra-long horizons, spanning scientific discovery, software engineering, combinatorial optimization, professional knowledge work, formal mathematics, and interactive games. Each task sustains at least 12 hours of continuous
agent operation under rich, multilevel feedback, and is built through substantial expert effort. We publicly release 51 tasks and our full evaluation framework to accelerate the study of how
agents learn from real world experience.
Read the full abstract ▾
All authors Deyao Zhu, Xin Zhou, Shengling Qin, Xuekai Zhu, Hangliang Ding, Shu Zhong, Zixin Wen, Zhonglin Xie, Chenhui Gou, Linxuan Ren, Yueyang Wang, Junfeng Zhong, Rui Liu, Tian Gao, Yangguang Lin, Jingyuan Zhang, Maojia Song, Xuan Qi, Jinhong Wu, Chenyang Zhang, Yinzhu Piao, Ziru Niu, Hongbin Lin, Lingxiang Meng, Peng Tang, Chengyao Tang, Shanyu Wu, Huanyu Zheng, Yu Liu, Liya Zhu, He Wang, Ming Ding, Ziyu Wan, Hao Liu, Sibo Wang, Haotian Zhu, Xintian Zhang, Nan Chai, Yipeng Liu, Panhao Lai, Sihang Yuan, Zixin Su, Ge Zhang, Wangchunshu Zhou, Yantao Du, Wenhao Huang, Guang Shi
Machine Learning · Cross-listed from stat.ML
Eli N. Weinstein and David M. Blei
Scientists often seek to draw causal inferences from structured data that is not independently and identically distributed, such as spatial data, network data, or molecular data. We develop
geometric causal models (GCMs), a framework for causal inference from dependent data that exploits underlying
symmetries of the data generating process. For example, in spatial data, we consider processes that are symmetric under translations, or in graph data, symmetric under permutations of the nodes. We show how
symmetries, formalized with group theory, can enable causal identification and estimation. We deploy ergodic theory for amenable groups to establish identification, and combine
geometric deep learning with scalable
Bayesian inference for estimation. We recover i.i.d. causal models and do-calculus when the data is a sequence and the
symmetry is permutation equivariance, and find novel types of causal models when we use alternate structures and
symmetries. As an example, we construct a causal model that satisfies the
symmetries of DNA. This GCM enables new
estimators for the effects of genetic variation, combining deep functional genomics models to describe outcomes and DNA
language models to describe propensities. We illustrate on semisynthetic data.
Read the full abstract ▾
Machine Learning
PDEFlow: Autonomous Agentic PDE Pipelines for Neural Operator Learning and Solver-Free Inference
Akshat Jani, Prathamesh Gadekar, Sakhinana Sagar Srinivas et al. (+1 more)
We present PDEFlow, an autonomous agentic framework that turns user-level ODE and PDE descriptions into solver-backed neural-operator pipelines. The workflow links problem specification, data generation, operator training, and checkpoint-based inference. A stateful input graph converts multi-turn natural-
language input and user edits into validated problem specifications. The data-generation module then samples parameters, solves the configured governing-equation with FEniCSx finite-element backend, and stores the solutions as operator-ready tensors. The training and inference stages use a registry-based interface, allowing different neural operators to be trained and deployed without changing the surrounding pipeline. In the current implementation, we instantiate this interface with a multi-branch
Bayesian DeepONet. Experiments on
benchmark ODE and PDE tasks show that PDEFlow can construct valid specifications, generate solver-backed
datasets, train neural operators across steady and transient problem classes, and provide solver-free predictions from saved checkpoints. The framework is designed for repeatable scientific and engineering workflows where many related physics configurations must be specified, simulated, learned, and queried with minimal manual intervention.
Read the full abstract ▾
All authors Akshat Jani, Prathamesh Gadekar, Sakhinana Sagar Srinivas, Venkataramana Runkana
Machine Learning · Cross-listed from physics.chem-ph
Physically-Relevant Information Learning in High-Dimensional Time-Derivatives Spaces
Domiziano Doria, Matteo Becchi and Giovanni M. Pavan
Understanding the physics of many-body complex dynamical systems may be a non-trivial task. High-dimensional analysis approaches are often deemed necessary to prevent losing important information. Typically, these use order parameters or descriptors capturing information related to, e.g., relative positions,
symmetries, etc., of the units in the studied system. However, in many cases, gaining information related to the relative positions of the constitutive units (or their velocities) alone may be insufficient, and to reach a more complete physical knowledge, one should ideally learn and correlate with each other both structure and dynamics. Here we demonstrate how to achieve such a goal efficiently by building and navigating high-dimensional Time-Derivatives (TiDe) spaces. A TiDe space can be generated for virtually any type of system/phenomenon from the time-series data collected along its observation over time. Each TiDe's dimension corresponds to a growing-order time-derivative of the extracted data, thus containing information related to different physical phenomena/events, which can be easily extracted via unsupervised approaches. We demonstrate how, by definition, TiDes can be directly analyzed without a need for prior dimensionality reduction, providing results that are intrinsically intuitive to interpret. We show the potential of the method by analyzing two prototypical example
datasets extracted from molecular dynamics simulations or experimental tracking of different types of complex dynamical systems. Our results demonstrate how efficiently one can navigate and learn in information-rich TiDe spaces, which provide a robust general framework for data analysis and for studying complex dynamical systems from the data collected along their observation over time.
Read the full abstract ▾