cs.LG · 2026-08-24 · No. 94
Machine Learning, 2026-08-24.
39 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
39 entries-
01
Asymmetric Capacity Allocation in Self-Refinement Pipelines
Zhuoyi Yang, Ian G. Harris, Salar Hashemitaheri, Cassie Huang, Yuangang Li, Hyunwoo Oh, Paul Dourish, Tony Givargis,...
cs.LG
Self-refinement, typically structured as generation, critique, and revision, is a widely adopted paradigm for improving LLM generation and serves as a core mechanism in many LLM agents. While the three stages involve different cognitive demands, most existing approaches conveniently treat the model size as an implementation detail rather than a subject of study, which may lead to a waste of resources. Little work has systematically examined...
-
02
Across-Design Uncertainty in Short Pricing Panels: Evidence from Simulated Price Trajectories
Pedro Cadahia Delgado
cs.LG · econ.EM
Short observational pricing panels can contain many observations while offering only a small number of distinct price movements. This paper studies the inferential consequences of that distinction in a synthetic data-generating process calibrated to a sparse pricing regime. We separate uncertainty conditional on a realised price trajectory from variation in estimation error across alternative trajectories generated by the same pricing...
-
03
Time-Aware Tranformer-Based Prediction Model for AECOPD
Weihao Qu, Ling Zheng, Dongyang Wang, Jiacun Wang, Haowen Pan
cs.LG
The rapid symptom change of Acute exacerbation of chronic obstructive pulmonary disease (AECOPD) makes it critical to have time-sensitive prediction models. However, most current machine learning models studying AECOPD use clinical and laboratory data, which will inevitably cause latency. To ensure timely detection of AECOPD and minimize latency, this paper focuses on home monitoring scenarios where only respiratory data from daily-use...
-
04
Rethinking Expressivity and Efficiency in Test-Time Training
Zeyun Zhong, Joya Chen, Manuel Martin, Frederik Diederichs, Juergen Gall, Juergen Beyerer
cs.LG
Test-Time Training (TTT) enables long-context processing via continuous weight updates during inference, but current methods struggle to balance the expressivity of per-token update dynamics with the hardware efficiency of chunk-wise approximations. We propose E$^2$-TTT (Expressive and Efficient TTT) to bridge this gap. Under the standard approximation of taking gradients at the chunk-start weights, we derive a closed-form state transition...
-
05
SPARCL: Spectral Partitioned Analytic Continual Learning
James Hartley, Zeropy Surio, Daniel Whitmore, Hannah Clarke, Thomas Reed
cs.LG
Analytic continual learning has emerged as a strong exemplar-free alternative to gradient-based class-incremental learning because it replaces iterative optimization with closed-form ridge updates. Yet the usual forgetting narrative, centered on stochastic gradient overwriting, does not explain why analytic methods still drift on old classes despite exact recursive solvers. We identify the culprit as spectral interference: the joint ridge...
-
06
ConceptTS: LLM-Guided Concept Bottlenecks for Interpretable Multivariate Time-Series Forecasting
Yichen Jiang, Yueqiao Chen, Dongyu Liu
cs.LG
State-of-the-art multivariate time-series forecasters can model complex temporal and cross-variable dependencies, yet their opaque representations provide limited insight into why a particular forecast is produced. This lack of transparency restricts their use in settings where practitioners must understand and assess the factors underlying a prediction. We introduce ConceptTS, an interpretable forecasting framework that organizes its...
-
07
TRACE-C: Rank-Calibrated Relational Anomaly Detection for Multi-Stream Operational Telemetry
Matthew Faucher
cs.LG · stat.ML
Operational telemetry can be jointly anomalous while every individual stream stays inside its familiar range. TRACE-C is an auditable strictly-prior rank-calibrated detector for aligned multi-stream telemetry: same-regime rolling median/MAD residuals feed three window channels -- a maximum normalized local sum, a Gaussian copula-form dependence contrast on robust-z residuals, and a worst standardized AR(1) innovation -- whose channel ranks...
-
08
Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness
Yu-Chao Huang, Haochen Zhang, Nicholas Konz, Tianlong Chen
cs.LG · cs.AI
Imputing physiological time series (arterial blood pressure, blood glucose, etc.) is essential for addressing the missingness that pervades clinical data. Yet modern imputation methods perform poorly in this domain: a recent benchmark found that simple linear interpolation outperformed every learned imputer on real-world clinical signals with realistic gaps. We show that this reflects two properties of physiological missingness that generic...
-
09
Tydra: An Efficient Hybrid Model for Tabular Data
Mieszko Komisarczyk, Saurabh Mathur, Maurice Kraus, Sriraam Natarajan, Kristian Kersting
cs.LG
Transformer-based tabular foundation models such as TabPFN achieve strong predictive performance but incur quadratic computational cost with context length. On the other hand, subquadratic SSM-based alternatives such as Hydra trade away accuracy for efficiency. To balance both, we introduce Tydra, a hybrid Transformer-State Space Model (SSM) architecture for tabular in-context learning that interleaves attention and SSM layers. Across 30...
-
10
A Neurosymbolic Approach for Constructing Planning Domain Models from Clinical Narratives
Ranveer Singh, Saurabh Mathur, Michael Skinner, Prasad Tadepalli, Kristian Kersting, Sriraam Natarajan
cs.LG
Surgical procedures such as laparoscopic appendectomy are complex, high-stakes processes, yet formalizing their workflows for decision support remains a significant challenge. Inducing probabilistic planning domain models in this setting is particularly difficult due to the lack of structured event data and the prevalence of implicit actions in clinical narratives, which neither empirical symbolic methods nor Large Language Models (LLMs) can...
-
11
Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI
Shiva Shrestha, Kazi Shaharair Sharif, Zongxing Xie, Jiajing Huang, Anhao Xiang, Honghui Xu
cs.LG · cs.DC
Federated fine-tuning enables large language models to adapt on edge devices without centralizing private data, but practical deployments must address hardware instability and adversarial update corruption together. Thermally constrained clients may throttle, slow local training, or delay synchronous aggregation, while Byzantine clients and communication-layer adversaries can corrupt the updates used to form the global model. To address these...
-
12
Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learning
Blaise Delaney, Dominic Dootson, Juan Jose Juan Castella, Salil Patel, Andrew Pfaff, Yuji Xing, Jonny Hancox, Karin Sevegnani
cs.LG
The cyclic structure of physiological processes offers a natural prior for self-supervised representation learning, and the cardiac cycle provides a particularly well-defined setting in which to exploit it. We derive a phase-equivariant self-supervised objective and introduce Winder, a joint-embedding architecture that organises representations into phase-invariant coordinates and phase-rotating harmonic subspaces. Its transport operator is...
-
13
COEC: Calibrated Orthogonal-Equivalence Compensation for Structured Pruning of Large Language Models
Peiqi Yu, Nam Ling, Wei Wang, Wei Jiang
cs.LG
Structured pruning reduces the size and inference cost of large language models (LLMs) by removing weight columns, but the resulting output error can degrade accuracy. Existing training-free compensation methods use an additive bias or a single orthogonal rotation on the output side of the retained weight. These corrections leave its input singular frame unchanged and therefore limit how the retained weight can adapt after column removal. We...
-
14
BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning
Mouhamed Amine Bouchiha, Gregory Blanc, Yufei Han
cs.LG · cs.CR · cs.DC
Decentralized Federated Learning (DFL) promises trust-free collaborative learning by replacing the centralized parameter server with peer-to-peer model exchange. However, this architectural shift fundamentally reshapes the threat landscape. Without globally coordinated aggregation, DFL becomes particularly susceptible to backdoor attacks, in which malicious participants implant persistent hidden behaviors while maintaining high clean-task...
-
15
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
Jiahong Liu, Ram Samarth B B, Xinyu Fu, Menglin Yang, Weixi Zhang, Rex Ying, Irwin King
cs.LG
Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph federated learning where clients possess structurally diverse graphs. Existing personalized federated learning (PFL) methods ignore the intrinsic geometric properties of diverse graph structures. We propose FlatLand, a novel personalized federated learning method that embeds different clients' data...
-
16
Causal Modeling of Adverse Pregnancy Outcomes via Adaptive LLM Proposals
Kavimayil P. Komarasamy, Saurabh Mathur, Ameet Soni, David M. Haas, Kristian Kersting, Sriraam Natarajan
cs.LG
Adverse Pregnancy Outcomes (APOs) such as preterm birth and gestational diabetes can have long-term consequences for both the mother and child, yet an understanding of their causes remains elusive. Causal discovery in this domain is especially challenging due to a paucity of data and incomplete domain knowledge. As a result, pure data-driven methods fail, and Large Language Model (LLM) outputs remain inconsistent or contradictory. We...
-
17
TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics
Yuhao Sun, Zekun Wu, Zixun Huang, Peijie Zhou
cs.LG · cs.AI · q-bio.GN
Inferring continuous system evolution from sparse temporal snapshots is a key challenge in generative modeling and single-cell omics. While Optimal Transport (OT) is popular, existing frameworks are largely restricted to first-order dynamics, assuming memoryless velocity fields. This limits expressiveness, as first-order systems fail to account for regulatory momentum and time-delayed responses inherent in processes like cell differentiation....
-
18
Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment
Emma Granqvist, Rocío Mercado, Samuel Genheden
cs.LG
Agentic large language model (LLM) systems are reshaping scientific workflows in chemistry and drug discovery, but evaluating their open-ended, tool-augmented outputs remains a fundamental bottleneck. Reference-based metrics such as BLEU and ROUGE fail to capture semantic correctness, while expert human evaluation does not scale to the iteration speed these systems demand. The LLM-as-a-Judge paradigm has emerged as a scalable alternative, but...
-
19
RODE: A Radial-Orthogonal Decoupled Engine for Optimization
Guoxiang Xu, Bince Qu, Qi Sun, Cheng Zhuo
cs.LG
Modern neural network training increasingly uses matrix-aware optimizers, yet their conditioned matrix step is typically added directly to the weight, jointly changing its norm and direction. This interaction matters because the current norm determines angular motion, while directional learning can drive norm growth and thereby alter later steps. We introduce RODE, which gives the radial and directional components separate update rules and...
-
20
Free-Probability Kernels for Zero-Rollout Hyperparameter Selection in Reservoir Computing
Sara Malacarne, Andrea Ceni, Claudio Gallicchio
cs.LG · cs.NE · stat.ML
Reservoir computing (RC) couples a fixed recurrent dynamical system with a trained lightweight readout, but this efficiency is partly lost during hyperparameter selection: the recurrent gain, input scale, and leakage rate determine the reservoir's stability and temporal processing regime and are usually tuned through many rollouts. We introduce a deterministic, pilot-informed selector for leaky linear reservoirs followed by coordinate-wise...
-
21
Trojaning the Alignment: Stealthy Backdoor Attacks against Graph Foundation Models
Minhua Lin, Zhicheng Gao, Yilong Wang, Hanqing Lu, Xiang Zhang, Suhang Wang
cs.LG
Graph Foundation Models (GFMs) on text-attributed graphs (TAGs) align graph representations with language semantics to support transferable graph learning. Despite these advantages, the backdoor vulnerability of GFMs on TAGs remains insufficiently understood, especially under graph-language alignment, where graph and text representations are trained to constrain each other in a shared semantic space. Existing backdoor attacks mainly target...
-
22
Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models
Deepanshu Pandey, Arnav Chavan, Nahush Lele, Sankalp Dayal, Deepak Gupta
cs.LG · cs.AI
Quantization of Large Language Models (LLMs) is often hindered by the sensitivity of the self-attention mechanism to discretization errors. We identify the softmax operator as a bottleneck for quantization stability due to its sensitivity to outliers and state-dependent Jacobian. We theoretically establish that suppressing the norm of this Jacobian helps in bounding quantization-induced performance degradation. Based on this, we propose...
-
23
A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Baselines
Kenneth Martin, Simon Heilig, Asja Fischer, Michel F. C. Haddad, Adam M. Sykulski, Moshe Eliasof
cs.LG · stat.ML
Graph neural networks (GNNs) are routinely employed for short-range forecasting on multivariate time series with a spatial graph structure. Despite the availability of many alternative datasets, method innovations within this domain are predominantly assessed against a rather limited set of benchmark datasets, most notably Chickenpox, PedalMe, WikiMaths, METR-LA, and PEMS-BAY. The evaluation protocols contain baselines spanning from...
-
24
Training, learning and inference: unified dynamics of neural systems
Mian Wang
cs.LG
We define an atomic generation fact f=(u,tau,omega,z;rho), recording the origin, realized transformation, concrete occurrence, generated result and relation role. Compiled into a Generation-Fact Graph (GFG), these facts provide an AI-native, compilable scientific fact substrate preserving generation histories. We establish a GFG-based recursive scientific process in which analysis, intervention, replay and validation form facts for later...
-
25
Decoupling Policy Extraction for Offline Reinforcement Learning
Xuyao Lin, Yixiang Shan, Jinru Duan, Tao Yang, Xinyu Zhao, Runyu Lei, Yiming Zhao, Jiaxin Fan, Zongbao Feng, Peng Jia
cs.LG · cs.RO
Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled learning process is well motivated in online RL, where an improved actor collects new data that can further update the actor and the critic. However, training data remains fixed in offline RL, making actor-side policy improvement unable to generate new data to validate or correct the critic....
-
26
Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs
Zifeng Liu, Zhiyong Du, Yaxin Lu, Yiming Mao, Zhenhe Wang, Wenqi Shi, Zhengkun Jing
cs.LG
Every way of teaching a deployed language model something new -- full fine-tuning, adapter merging, model editing -- replaces the released checkpoint, and with it every evaluation and cache that referred to those exact bits. We instead learn inside the dequantization gap: with the integer codes and scales of a 4-bit release frozen, new knowledge is written only into the per-weight residual that lives strictly inside each quantization decision...
-
27
Scaling Muon for Diffusion Transformers
Chenghao Li, Xiao Han, Xinxin Huang, Wei Liu, Boyang Li, Bing Xiao, Heran Zhang, Juanma Perez Rua, Ke Xu, Kangning...
cs.LG · cs.AI · cs.CV
The matrix-aware optimizer Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-end efficiency on large Diffusion Transformers (DiTs) remain unclear. We first establish Muon's scaling behavior on DiTs from 1.3B to 15B parameters, showing that its optimization and generative quality advantages over AdamW persist across model scales. However, at scale, the 5-step Newton--Schulz...
-
28
Resolution-Consistent Greedy Neural Approximation on Infinite-Dimensional Spaces
Pablo M. Berná, Antonio Falcó, Diego Mondéjar
cs.LG · math.FA
We develop constructive approximation and learning guarantees for shallow neural models with infinite-dimensional inputs observed through finitely many coordinates. The analysis is based on a parameter-normalized neural dictionary and its associated weighted variation class. Within this class, the approximation error separates into a distribution-dependent coordinate-truncation term and a greedy finite-width term. For empirical regression, a...
-
29
Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting
Lan Guo, Jie Xiao, Zhao Su, Jun Shen, Haoran Li, Weixia Ma, Qingguo Zhou, Binbin Yong
cs.LG · cs.AI
In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous latent dynamic states, while existing deep forecasting models usually compress them into a unified end-to-end mapping, leading to suboptimal modeling of time-varying dynamics and limited interpretability regarding which forecasting mechanism is activated under different latent states. To overcome these limitations, we reformulate time...
-
30
Hidden Axis of Uncertainty: Latent-Posterior Alignment in Graph Neural Networks with Bayesian Output Layers
Suk Hoon Choi, Damdae Park, Junhyuk Choi, Hyein Jung, Changsoo Kim, Ung Lee, Kyeongsu Kim
cs.LG
Bayesian Neural Networks (BNNs) with Bayesian output layers provide a principled and tractable framework for quantifying predictive uncertainty, yet the mechanisms shaping that uncertainty remain unclear. While conventional theory attributes uncertainty reduction to posterior contraction, the corresponding assumptions need not hold for deep models. In the Graph Neural Networks (GNNs) with Bayesian output layers studied here, we observe that...
-
31
Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges
Hongyang He, Xinyuan Song, Yan Zhong, Daizong Liu, Yanbin Li, Yang-fan He, Wenqiao Zhang
cs.LG
Real-world semi-supervised learning (SSL) often encounters significant challenges with long-tailed label distributions and noisy pseudo-labels, which hinder generalization and amplify confirmation bias. In this work, we introduce a novel framework, Gaussian Bridge Consistency (GBC), to address these challenges by constructing semantic interpolation paths between unlabeled samples and high-quality class anchors. Our method maintains a dynamic...
-
32
Reinforcement Learning for Continuous-Time Jump Markov Decision Processes with Applications to Network Dynamic Pricing
Huiling Meng, Ningyuan Chen, Xuefeng Gao
cs.LG
We study reinforcement learning (RL) in Continuous-Time Jump Markov Decision Processes (CTJMDPs) featuring general discrete state spaces (which need not possess a vector space structure) and continuous/discrete action spaces. The setup covers many well-known applications in operations such as multi-product dynamic pricing with capacitated resources (Gallego and van Ryzin 1997). To model the exploration-exploitation tradeoff, we formulate an...
-
33
Lightweight Adaptive ReduNet via Hyperspherical Manifold Learning
Zhenglin Huang, Qifa Yan, Bin Dai, Xiaohu Tang
cs.LG · cs.AI
In recent years, a white-box neural network called ReduNet has been proposed, which employs the maximal coding rate reduction (MCR$^2$) principle to transform raw data into low-dimensional discriminative features via a forward layer-wise construction process. Unlike traditional deep networks that rely on backpropagation, ReduNet explicitly derives the parameters of each layer from the features of its preceding layer, offering a mathematically...
-
34
C-Score: Beyond Accuracy for Robustness Assessment in Semi-Supervised Learning under Open-World Unlabeled Contamination
Tsao-Lun Chen, Chi-Cheng Fu, Han-Yi E. Chou, Shun-Feng Su
cs.LG · cs.AI
Pseudo-label-based semi-supervised learning has achieved strong performance due to its simplicity and scalability. However, it is typically developed under a closed-world assumption that unlabeled data are drawn from the same distribution as labeled data. In practical deployment, unlabeled data are often collected from open environments and may contain OOD samples. Under such contamination, OOD samples may still receive high-confidence...
-
35
RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction
Guangyu Wang, Zhidan Liu
cs.LG · cs.AI
Traffic sensors commonly record flow, speed, and occupancy, but standard traffic flow forecasting benchmarks and models rarely exploit all three raw measurements reliably. Although speed and occupancy provide sensor-native traffic-state information beyond flow alone, existing releases often omit these variables, replace them with proxies, or contain logically inconsistent records. Moreover, direct empirical risk minimization over...
-
36
Meta-clustering of milk mid-infrared spectra identifies dairy cow groups associated with negative energy balance in early lactation
T. Touil, E. R. Paquet
cs.LG
Clustering methods have been used to identify distinct groups of milk samples, cows, or herds. Fourier-transform infrared (FTIR) spectroscopy, particularly mid-infrared (MIR) spectroscopy, has been applied to individual cow milk samples to predict various milk traits. Applying clustering directly to MIR spectral data may reveal latent groups of cows associated with milk traits or health disorders and can help prevent these conditions or...
-
37
Provable Edge-of-Stability for Adam on a One-Dimensional Quadratic
Yiman Fong, Heng Yang
cs.LG · cs.AI · math.OC
The edge-of-stability (EoS) phenomenon of Adam has been widely observed, while its underlying dynamical mechanism is not yet fully understood. We study uncorrected Adam on a one-dimensional quadratic, a clean setting where constant curvature isolates the optimizer-induced dynamics behind the EoS. We characterize the resulting dynamics across the parameter space. In broad regimes, we prove that Adam exhibits a restoring tendency toward its...
-
38
Faults That Fortify: CNN Adversarial Robustness via GPU Undervolting
Behnam Omidi, Ahmad Tahmasivand, Husam Alsyouri, Saba Al-Sayouri, Chongzhou Fang, Ihsen Alouani, Khaled N. Khasawneh
cs.LG · cs.AR · cs.CR
Convolutional Neural Networks (CNNs) face a dual challenge: vulnerability to adversarial attacks and prohibitive training cost. Adversarial training is effective but expensive, a burden that grows as learning shifts to the energy-constrained edge. This paper addresses both through GPU undervolting during training. Reducing supply voltage introduces stochastic perturbations that act as implicit regularization, improving robustness while...
-
39
AgentDecarbonizer: Carbon-Aware Execution for AI Agents
Leyi Yan, Shuangning Li, Sihang Liu
cs.LG
AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, invoke tools, and interact with external environments. These workflows enable tasks such as software repair, data analysis, and experiment management, but their repeated model invocations can incur substantial carbon emissions. This paper characterizes the carbon emissions of OpenClaw agent...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.