cs.LG · 2026-09-25 · No. 124

Machine Learning, 2026-09-25.

45 new papers in cs.LG. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

45 entries
  1. 01

    Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning

    Sudip Bhujel, Shanghao Shi, Ruiquan Huang, Ning Zhang, Yang Xiao

    cs.LG

    Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal structure can amplify this leakage beyond single-frame attacks. We introduce Temporal Reconstruction Attack on Consecutive Encodings (TRACE), an amortized temporal gradient-inversion attack that autoregressively reconstructs the sequence of private...

    arxiv.org/abs/2609.30258 · PDF

  2. 02

    To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech

    Debajyoti Mazumder, Mamta, Abhirama Subramanyam Penamakuri

    cs.LG · cs.AI · cs.CL · cs.SD

    Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VeriSpeak, a probe benchmark for studying speech-based fact verification in Large Audio Language Models (LALMs). VeriSpeak contains 3,879 spoken claims spanning temporal, geographical, and...

    arxiv.org/abs/2609.30227 · PDF

  3. 03

    PoEM: Predicting RL Outcomes from Existing Policies

    Kimia Hamidieh, Giannis Daras, Antonio Torralba

    cs.LG · cs.AI · cs.CL · cs.CV

    Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as human alignment, correctness, or instruction following. This post-training process is computationally intensive, sometimes unstable, and has to be run from scratch every time the reward model changes or when we want to combine multiple rewards. We hence ask: given a new reward function, is it possible to predict the RL outcomes without...

    arxiv.org/abs/2609.30226 · PDF

  4. 04

    Minimally Invasive Steering of Language Models

    Taha Entesari, Jingyu Zhang, Daniel Khashabi, Mahyar Fazlyab

    cs.LG · cs.AI

    Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the output distribution and degrade generation quality. We propose Minimally Invasive Steering Vector Optimization (MISVO), which penalizes interventions using the local KL geometry of the induced token distribution. The resulting Fisher quadratic measures...

    arxiv.org/abs/2609.30218 · PDF

  5. 05

    Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers

    Andreas E. Robertson, Ashley T. Lenau, John D. Shimanek, Benjamin A. Jasperson, Vivek Oommen, David L. Damm, Krishna...

    cs.LG · cond-mat.mtrl-sci · cs.CE

    Latent neural surrogate solvers, or latent dynamics models, accelerate simulations of time-dependent physical systems by evolving a compressed latent space rather than resolving full-resolution fields directly. In principle this reduces computational cost and simplifies learning, but in practice errors often accumulate rapidly during long autoregressive rollouts, limiting predictive utility. We show that this instability does not stem from...

    arxiv.org/abs/2609.30198 · PDF

  6. 06

    Intrinsic-Extrinsic Coupling in Learning Dynamics

    Qinyou Wang

    cs.LG · stat.ML

    A learner's current observations need not determine its response to further training. We formulate intrinsic-extrinsic coupling through the continuation-conditioned value of a constrained learning-state intervention, with observation-relative fibers describing present agreement. An executable finite-frame classifier-head write protects current logits while repairing specified historical margins under finite-precision acceptance checks. We...

    arxiv.org/abs/2609.30185 · PDF

  7. 07

    Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management

    Giacomo Arcieri, Gregory Duthé, Christophe Muller, Konstantinos G. Papakonstantinou, Daniel Straub, Eleni Chatzi

    cs.LG

    Modern infrastructure asset management constitutes a complex sequential decision-making problem, characterized by long planning horizons and system-level interactions, such as spatial deterioration correlations and economies of scale. While deep reinforcement learning has shown promise in optimizing maintenance policies, scaling to real-world networks remains challenging. Centralized approaches become computationally intractable in...

    arxiv.org/abs/2609.30150 · PDF

  8. 08

    On the SoS Certifiability of Log-Concave Distributions

    Aleksandr Storozhenko

    cs.LG · cs.CC · math.PR

    For an arbitrary isotropic log-concave distribution $P$ on $\mathbb{R}^d$, we prove that the polynomial $(Cm)^m\|v\|_2^m - \mathbb{E}_{X\sim P}\langle X,v\rangle^m$ is a sum of squares for every even $m\ge2$, where $C>0$ is a universal constant. This removes the dependence on the Poincaré constant in the theorem of Kothari and Steinhardt (arXiv:1711.07465), recovering the optimal moment bounds for log-concave distributions. As an immediate...

    arxiv.org/abs/2609.30105 · PDF

  9. 09

    AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs

    Xiaochen Zhang, Haoyu Zhu, Yao Zhang, Qingchun Hou

    cs.LG · cs.AI · math.OC

    Graph-structured optimization with linear constraints is fundamental to critical infrastructure but faces scalability limits due to massive strict hard constraints and high dimensionality. While recent projection-based methods such as Trainable Sampling Kaczmarz-Motzkin Net (T-SKM-Net) guarantee feasibility, they face high computational costs in dynamic environments by processing the entire constraint set and requiring expensive matrix...

    arxiv.org/abs/2609.30088 · PDF

  10. 10

    Residual Correlation as a Diagnostic for Joint-Uncertainty Gains from GP Coregionalisation

    Fangqin Zhou, Joaquin Vanschoren

    cs.LG

    In multi-target regression, correlated targets are often coupled through multi-output Gaussian processes with an intrinsic model of coregionalisation (GP-ICM), assuming that sharing statistical strength improves overall performance. In practice, the benefits are inconsistent. Across the settings studied, we find that the main benefit of coregionalisation is joint uncertainty quantification rather than point prediction. Raw target correlation...

    arxiv.org/abs/2609.30085 · PDF

  11. 11

    Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features

    Anne M. Tumlin, Ben Wooding, Zhenxuan Shao, Diego Manzanas Lopez, Tyler Derr, Taylor T. Johnson

    cs.LG · cs.AI

    Graph neural networks (GNNs) have become a prominent approach for developing fast, topology-aware surrogates in electric power systems, supporting tasks such as power flow (PF) analysis, optimal power flow (OPF) estimation, and cascading failure analysis (CFA). Despite this growing use, formally verifying GNN-based models remains challenging, with existing methods limited in scope. We extend the neural network verification (NNV) framework to...

    arxiv.org/abs/2609.30079 · PDF

  12. 12

    Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think

    Xvyuan Liu, Jianjie Fang, Chen Gao, Yong Li

    cs.LG · cs.RO

    Planners built on visual world models commonly score each predicted outcome by its distance to the encoded goal image. We show that this target can limit control even with exact dynamics and globally optimal short-horizon search: reaching a goal may require actions that initially move away from it. With frozen LeWM models, intermediate targets substantially improve action synthesis and recorded-action ranking on Cube, PushT, Reacher, and...

    arxiv.org/abs/2609.30036 · PDF

  13. 13

    Canopy: Exploiting Piecewise Smooth Tree Priors for Multi-Fidelity Bandits

    Michael Jerge, Suman Jana

    cs.LG · cs.AI

    Many LLM inference problems, including model routing, prefix-cache management, prompt trimming, and test-time search, can be viewed as optimization over a tree. This structure arises naturally from autoregressive generation: every prefix defines a node, and its continuations form a subtree below it. Internal nodes of the tree provide cheap but biased estimates of a region's value, while leaf evaluations are expensive but accurate....

    arxiv.org/abs/2609.30017 · PDF

  14. 14

    Let Training Guide Selection: Online Synthetic Data Filtering via Real-Anchored Utility

    Yanran Wu, Sana Lakdawala, Renzo Tassara Miller, Chongyang Bai, Sharath Ciddu, Shivendra Pratap Singh, Kungang Li,...

    cs.LG

    Synthetic data can scale training supervision when real-world data are limited, but noise and distribution mismatch can reduce its value. Existing synthetic data selection methods often emphasize fidelity or diversity rather than the learner's evolving needs. We propose FROST, an online framework that estimates synthetic-data utility through gradient feedback anchored in real training data. It calibrates batch utility against recent history...

    arxiv.org/abs/2609.29988 · PDF

  15. 15

    Diverse Geometries, Frozen Weights: Robust Heterogeneous Treatment-Effect Estimation via Causal Expert Ensembles

    Ali Haghpanah Jahromi, Mohammad Taheri

    cs.LG

    Estimating heterogeneous treatment effects from observational data is difficult because the most appropriate inductive bias varies with overlap, treatment imbalance, prognostic structure, and sample size. We introduce the Geometry-Diverse Anchor-Correction Expert Ensemble (GeoACE), a five-expert framework that combines a common anchor-correction estimator with complementary overlap-aware and outcome-guided geometries. Its task-level ensemble...

    arxiv.org/abs/2609.29974 · PDF

  16. 16

    A Contraction Framework for Stochastic Operators with Bootstrapping: Application to TD Learning

    Ids van der Werf, Sergio Rozada, Antonio G. Marques

    cs.LG · eess.SP · math.OC

    Many iterative algorithms rely on bootstrapping. A variable is updated using a second, frozen copy as a target, which is periodically replaced with the updated variable. Majorize-minimize and inexact proximal-point methods share this structure, as does temporal-difference (TD) learning. However, existing convergence guarantees for scenarios that combine sampled updates with targets refreshed only every $K$ steps rely on the specific structure...

    arxiv.org/abs/2609.29961 · PDF

  17. 17

    Beyond Average Safety: Chance-Constrained LLM Fine-tuning

    Taha Entesari, Mahyar Fazlyab

    cs.LG · cs.AI

    Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also induce regressions on safety-critical prompts. Existing safety-preserving fine-tuning methods typically control average safety loss or use weighted auxiliary penalties, which can obscure rare but severe failures. We propose a chance-constrained formulation for safety-preserving fine-tuning that...

    arxiv.org/abs/2609.29960 · PDF

  18. 18

    Tracking States or Tracking Cosets? An Algebraic Account of Learned State Tracking

    Zhiyu Zhang, Yupeng Li

    cs.LG · cs.AI

    State tracking requires composing a sequence of updates, but accuracy alone does not reveal what a model has learned. We study neural networks trained to predict the running product of group elements. We identify quotient solutions in Transformers, where models recover the quotient class while predicting nearly uniformly among its members. The reciprocal of class size predicts partial accuracy without a fitted parameter, extending...

    arxiv.org/abs/2609.29951 · PDF

  19. 19

    Error- and Prediction-Driven Motor Learning in the Cortico-Cerebellar Loop

    Ana Carolina Filipe, Rui Ponte Costa, Cláudia Soares

    cs.LG

    Robust control under delayed sensory feedback remains a key challenge in both robotics and neuroscience. Classical cerebellar models explain delay compensation through forward prediction but fail to account for fast online corrections and rapid adaptation observed in biological systems. We propose a cerebellum-inspired control framework that combines multiplexed predictive representations with internal feedback. By jointly encoding kinematic...

    arxiv.org/abs/2609.29945 · PDF

  20. 20

    MF-SCBO : Multi-fidelity Scalable Constrained Bayesian Optimization

    Lucas Palazzolo, Mickaël Binois, Laëtitia Giraldi

    cs.LG · math.OC

    Many real-world optimization problems rely on expensive simulations or experiments, making the efficient use of available data essential. Multi-fidelity optimization of high-dimensional black-box functions subject to black-box constraints is increasingly relevant as the cost of objective evaluations continues to rise in applications such as machine learning, engineering, and control. To our knowledge, no existing method simultaneously...

    arxiv.org/abs/2609.29941 · PDF

  21. 21

    When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers

    Qingyu Wu, Yuan Wei, Renju Liu, Hua Cheng

    cs.LG · cs.AI · cs.CR

    Wearable human-activity recognition (HAR) models operate across sensors, subjects, and backbones, yet a smooth waveform may appear temporal while exploiting a persistent sensor offset primarily. We introduce SpectrumAudit, a label-sealed audit that fits a phase-randomized full-window stimulus on calibration windows from subjects held out from training and testing. After selection, it replays its exact DC projection and budget-constrained...

    arxiv.org/abs/2609.29937 · PDF

  22. 22

    Improving Calibration of Black-Box Radiology AI Using Test-Time Augmentation

    Nathan Le, Magdalini Paschali, Arogya Koirala, Andrew Johnston, Zhongnan Fang, David B. Larson, Akshay S. Chaudhari,...

    cs.LG · cs.HC

    Radiology AI systems increasingly inform clinical decisions such as triage, follow-up imaging, and treatment planning. For these decisions to be made safely, model outputs must be well calibrated, meaning predicted probabilities accurately reflect true risk. Many standard techniques for improving calibration, such as MC Dropout and Deep Ensembles, require access to model parameters or retraining. However, proprietary clinical AI systems...

    arxiv.org/abs/2609.29931 · PDF

  23. 23

    Spatio-temporally complementary feature propagation on graphs for longitudinal AADT estimation

    Linghang Sun, Qishen Zhou, Michail A. Makridis, Anastasios Kouvelas

    cs.LG

    The estimation of Annual Average Daily Traffic (AADT) is vital for transportation planning and infrastructure maintenance, yet obtaining accurate values for an entire urban network across multiple years remains challenging due to the high cost and spatial sparsity of physical sensors. This research proposes a novel spatio-temporally complementary feature propagation framework that leverages the strengths of two distinct data sources:...

    arxiv.org/abs/2609.29906 · PDF

  24. 24

    From Graphs to Feeders: Constraint-Guided Diffusion for Rule-Compliant Feeder Generation

    Yu Qin, Andrew Glaws, Aadil Latif, Ryan King

    cs.LG

    Generative modeling approaches often focus on recovering broad statistical characteristics from the training data. In the context of graph generation, this may refer to degree distributions, clustering coefficients, or spectral properties. However, generating usable distribution feeders when detailed feeder models are unavailable requires more than matching generic graph statistics: the sampled topology must also obey electrical compatibility...

    arxiv.org/abs/2609.29879 · PDF

  25. 25

    SwitchPFN: Shared Switching Dynamics for Frozen In-Context Time Series Classification

    Zhenyi Zhu, Jacqueline Pang, Peilin Shen, Tianyi Song, Tingwei Zhang, Keyi Hu, Kangjun Yin, Shiwei Pu, Yingbo Zhou, Chen Shao

    cs.LG

    Tabular foundation models (TFMs) provide a promising route to time-series classification, but their effectiveness depends on how sequential data are converted into tabular representations. Existing representations face two challenges: global aggregation can lose the order of temporal evolution, while features computed in independently fitted coordinate systems may not have consistent meanings across sequences. We therefore view representation...

    arxiv.org/abs/2609.29814 · PDF

  26. 26

    FlashLoop: Fast and Memory-Efficient Looped Transformers via Lazy Updates

    Wanqi Yang, Shiwei Liu

    cs.LG

    Looped Transformers have attracted substantial attention as a parameter-efficient approach to increasing computational depth through repeated application of shared Transformer blocks. However, their practical advantages over conventional Transformers remain under debate: each additional loop incurs another Transformer pass and requires caching another set of KV states, causing inference FLOPs and KV-cache memory to grow continuously with loop...

    arxiv.org/abs/2609.29812 · PDF

  27. 27

    An Analytical Theory of Auxiliary Learning

    Federico Milanesio, Alessandro Ingrosso, Matteo Osella

    cs.LG

    Auxiliary learning is an optimization paradigm in which a neural network's performance on a target task is improved by jointly training it on additional tasks. However, the mechanisms behind this improvement remain poorly understood. We study this problem using a teacher-student framework and derive a closed system of differential equations describing the dynamics of online stochastic gradient descent in the large-input limit. For linear...

    arxiv.org/abs/2609.29774 · PDF

  28. 28

    WeatherDiagFlow: Evidence-Grounded Radar Nowcasting with Diagnostic Flow Refinement

    Chunlei Shi, Yufeng Zhu, Yixiao Liang, Dan Niu, Yongchao Feng, Qiliang Wu, Jiong Wang

    cs.LG · cs.MM

    Radar nowcasting is essential for short-term warning and emergency response, yet conventional systems mainly return future radar fields and provide limited support for operational communication and post-event verification. We formulate radar nowcasting as an evidence-grounded forecast--bulletin--audit task, in which a numerical forecaster produces both future radar fields and structured diagnostic evidence. Forecast-time bulletins use only...

    arxiv.org/abs/2609.29772 · PDF

  29. 29

    TopU-LBVS: A Realistic Multi Target Benchmark for Ligand Based Virtual Screening

    Surbhi Kumar, Yuhe Zhou, Varun Shiralkar, Niu Huang, Baris Coskunuzer

    cs.LG · cs.AI

    Ligand-based virtual screening (LBVS) is a practical first-pass tool in early-stage drug discovery, but existing benchmarks can overestimate performance through random negatives, easy decoys, limited target coverage, and non-standardized evaluation protocols. We introduce TopU-LBVS, a multi-target benchmark for LBVS under hard-negative screening conditions. Starting from curated ChEMBL~35 bioactivity data, TopU-LBVS covers 93 protein targets...

    arxiv.org/abs/2609.29740 · PDF

  30. 30

    Direct Message Approximation (DMA): A Consistency-Based Framework for Tractable Approximate Inference on Factor Graphs

    Ralf Herbrich, Rainer Schlosser, Jan Lemcke, Johann Ukrow, Anna Kazachkova, Nicolas Alder, Leonhard Hennicke, Theo...

    cs.LG · cs.AI · stat.ML

    Approximate message passing on factor graphs underlies two dominant families of probabilistic inference algorithms: expectation propagation (EP) and variational message passing (VMP). Both methods approximate the marginal at each factor edge, forcing an iterative round-robin schedule, risking negative-precision messages, and, for VMP, collapsing to point estimates at Dirac-delta factors. We introduce Direct Message Approximation (DMA), which...

    arxiv.org/abs/2609.29466 · PDF

  31. 31

    Precise Convergence Speed of Clipped SGD

    David A. R. Robin

    cs.LG · math.OC

    We present a tightened convergence analysis of clipped gradient descent on $(L_0, L_1)$-smooth functions, with quantitative constants. Building on the ideas of Koloskova et al (2023), we refactor several case disjunctions to reveal the central role of a control of the bias derived from fundamental properties of $\ell_2$-projection, simplifying proofs. We also extend the domain of validity from $η\leq 1 / (9 β)$ to $η< 1 /β$ where $β= L_0 + c...

    arxiv.org/abs/2609.29458 · PDF

  32. 32

    Decoupled Learning and Selection in Slate Recommendation for Privacy and Stability Under Noisy Scores

    Sam Urmian, Qinyi Liu, Mohammad Khalil

    cs.LG · cs.IR

    We formalize slate recommendation as a randomized score learner followed by deterministic selection. First, an appropriately scoped differential-privacy guarantee passes through selection and its audit trace by post-processing. End-to-end privacy holds only when selector inputs are public or independent, previous private outputs, or separately privacy-accounted; fixing raw state or candidate information instead yields only a conditional...

    arxiv.org/abs/2609.29453 · PDF

  33. 33

    SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM

    Mengli Wei, Mengkai Zhu, Jiawen Chen, Wenwu Yu, Duxin Che

    cs.LG · cs.NI

    Reducing communication in derivative-free decentralized learning requires controlling the disagreement accumulated over multiple local updates. This paper develops SPADE-DFL, a primal--dual method that allows the number of local function-value updates between neighbor exchanges to grow with the computation budget while preserving the nonprivate convergence order. For smooth nonconvex objectives under uniform query-moment bounds, the...

    arxiv.org/abs/2609.29446 · PDF

  34. 34

    Neural Transport Nested Sampling

    David Yallup, Will Handley

    cs.LG · stat.ML

    Sampling from Boltzmann distributions of molecular systems is an inference problem that has seen significant recent developments fuelled by advances in neural density estimation. We develop a novel sampling algorithm, Neural Transport Nested Sampling (NTNS), which combines the classical strengths of nested sampling with modern neural flow-based methods. NTNS uses a flow matching velocity as the drift in a Metropolis--Hastings corrected...

    arxiv.org/abs/2609.29413 · PDF

  35. 35

    ICE: Task-Aligned Clifford Latent Fields for Multimodal Graph Foundation Models

    Xunkai Li, Xu Wang, Yinlin Zhu, Xiong Yongfu, Yi Liu, Rong-Hua Li, Guoren Wang

    cs.LG

    Multimodal attributed graphs connect entities, visual content, language, and observed relations. Learning one foundation across such graphs requires more than compressing each node into a fused Euclidean vector. The representation must preserve entity semantics, construct interaction state from graph neighborhoods, and expose that state to prediction units with different geometry. Our empirical study shows why these requirements are...

    arxiv.org/abs/2609.29398 · PDF

  36. 36

    MORE-PLR: multi-output regression employed for partial label ranking

    Santo M. A. R. Thies, Juan C. Alfaro, Viktor Bengs

    cs.LG

    The partial label ranking problem is a supervised learning scenario that aims to fit a preference model that predicts a bucket order defined over a set of labels for a given input instance. This problem generalizes the well-known label ranking problem, which, in practice, is limited to outputting total orders of labels. Existing partial label ranking methods have primarily extended label ranking approaches to handle ties in predictions. This...

    arxiv.org/abs/2609.29386 · PDF

  37. 37

    Lightweight Probabilistic Downscaling from a Deterministic Base Model

    Joseph McLean, Tiffany Vlaar, Sigrid Passano Hellan, Linus Ericsson

    cs.LG

    Climate data downscaling is the task of increasing the spatial resolution of climate data, typically by generating fine-resolution regional climate data from coarse global model output. Recent machine learning (ML) work in the related task of weather forecasting has seen significant improvements due to newly devised training methods and architectural components, but these have not yet benefited downscaling. We adapt two of these methods to...

    arxiv.org/abs/2609.29383 · PDF

  38. 38

    On the second-order optimization for spiking neural networks

    Ngoc Phu Doan, Ihsen Alouani

    cs.LG · cs.CV

    Spiking Neural Networks (SNNs) offer an energy-efficient alternative to conventional neural networks by exploiting sparse, binary spikes, and event-driven computation. However, the training of SNNs remains challenging, as spiking activations create a sharp loss landscape that hinders training, and diagonal-curvature optimizers such as the Adam family may fail to capture this geometry. The extension of curvature-based optimization methods to...

    arxiv.org/abs/2609.29379 · PDF

  39. 39

    FlowAtom: Atom-Based Evidence Aggregation for Multi-Label Website Fingerprinting

    Chongru Fan, Wentao Huang, Wei Wang, Zhenquan Ding, Jinqiao Shi, Wei Cai, Zhiyu Hao

    cs.LG · cs.NI

    Identifying the set of monitored websites in mixed encrypted traffic is challenging because an individual flow often provides only partial evidence of website identity. To address this challenge, we propose FlowAtom, which constructs shared prototypes, called Atoms, from flow representations without website labels. Specifically, FlowAtom pretrains a flow encoder on external unlabeled traffic and aggregates Atom responses across flows within...

    arxiv.org/abs/2609.29330 · PDF

  40. 40

    TinyCardioUNet: IMU-to-ECG Translation with Graph-Encoded Inter-Axis Dependencies and Tensor Decomposition-Based Parameter Reduction

    Seungwoo Han, Ingon Chanpornpakdi, Motoi Noda, Puwadej Leelasiri, Ibuki Hiruma, Toshihisa Tanaka

    cs.LG

    Estimating electrocardiography (ECG) from a chest-worn inertial measurement unit (IMU) enables continuous heart rate (HR) monitoring without the discomfort of electrodes. We propose TinyCardioUNet, a lightweight UNet that uses all six IMU axes without prior channel selection, refines its bottleneck with a graph neural network that encodes inter-axis dependencies, and employs tensor decomposition with automatic variational Bayesian rank...

    arxiv.org/abs/2609.29322 · PDF

  41. 41

    Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting

    Xiaohan Jiang, Jingyuan Wang, Jiahao Ji, Yongyao Wang, Chen Yang, Junjie Wu

    cs.LG · cs.AI

    Time series analysis is fundamental in domains such as finance, healthcare, and meteorology. Real-world time series often exhibit multiscale characteristics shaped by diverse latent factors, resulting in intricate temporal patterns and rich frequency structures. However, existing approaches typically focus on either frequency-domain decomposition or time-domain pattern extraction in isolation, neglecting their joint structure. This decoupled...

    arxiv.org/abs/2609.29317 · PDF

  42. 42

    Beyond Feature Reliability: Repeat-Informed Multifractal Curve Regression for Brain-Age Prediction

    Yu Chang, Anzhe Cheng, Jiahao Chen, Heng Ping, Peiyu Zhang, Puquan Pan, Tamoghna Chattopadhyay, Sophia Thomopoulos,...

    cs.LG

    Brain-age prediction from resting-state fMRI provides a quantitative framework for characterizing age-related changes in spontaneous brain dynamics and for identifying functional signatures. Existing studies have linked fractal and multifractal scaling to age and examined the reliability of individual features. However, prediction repeatability depends on how features fluctuate jointly and how a predictor combines them, which feature-wise...

    arxiv.org/abs/2609.29307 · PDF

  43. 43

    Online Task Adaptation via Self-Organisation

    Krsto Proroković

    cs.LG · cs.NE

    Neural networks are typically adapted by computing gradients and updating model parameters. We investigate whether task-specific adaptation can instead emerge from a meta-learned self-organising process that requires no gradients at adaptation time. We instantiate this idea with a Neural Cellular Automaton in which locally interacting recurrent cells maintain both a recurrent state and a fast associative memory. During meta-training,...

    arxiv.org/abs/2609.29281 · PDF

  44. 44

    Learnable Time-Frequency Masks for Explaining Time-Series Classifiers

    Theresa Dahl Frehr, Francisco Pelayo, Lukas Raad, Alicia García Sanz, Thea Brüsch, Tommy Sonne Alstrøm

    cs.LG

    Time-series explainability remains challenging because discriminative information is often encoded in latent frequency or time-frequency features rather than in the raw signal itself. Existing attribution methods typically operate either in the time domain or in a fixed transform domain, limiting their ability to capture salient information across different representations. We propose XACT, a general framework that learns sparse attribution...

    arxiv.org/abs/2609.29270 · PDF

  45. 45

    BridgeMem: Causal Dyadic Transition Residuals for Temporal Knowledge Graph Forecasting

    Zeyan Li, Libing Chen, Shengda Zhuo, Yin Tang, Jianfeng Xu

    cs.LG

    Temporal knowledge graph forecasting aims to infer future relational facts from the temporal structure of observed events. Existing forecasters mainly summarize history through entity states, relation states, paths, or exact recurrence. These views often miss pair-specific transition evidence, that is, the way prior relations between the query actor and a candidate change the odds of the target relation. We introduce BridgeMem, which...

    arxiv.org/abs/2609.29268 · PDF

This edition is part of The Daily Abstract — cs.LG archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.