cs.LG · 2026-08-26 · No. 96
Machine Learning, 2026-08-26.
57 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
57 entries-
01
Improving Cross-Problem Vehicle Routing with Locally Augmented Preferences and Representation Disentanglement
Arthur Corrêa, Paulo Nascimento, Samuel Moniz
cs.LG
Multi-task vehicle routing problem (VRP) solvers seek to handle multiple VRP variants within a single unified model, avoiding the need to train a separate model for every variant. In spite of recent progress, current approaches remain limited on two fronts. On the training side, reinforcement learning suffers from reward-scale disparities and shrinking advantage signals as policies improve, whereas preference optimization stagnates once...
-
02
Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learning
Lars van der Laan, Nathan Kallus
cs.LG · stat.ML
Marginalized importance weighting evaluates a target policy by reweighting offline state-action samples with its discounted occupancy ratio, characterized by an adjoint Bellman equation. Existing minimax, primal-dual, and fitted fixed-point estimators can leave residual occupancy-balance violations because of function-class approximation, regularization, or incomplete optimization. These violations are difficult to diagnose and reduce because...
-
03
BioKERN: Biological Kernel Regularization for Histology-to-Transcriptomics Neighborhood Retrieval
Seungik Cho, Betul Orcan-Ekmekci
cs.LG · q-bio.QM
Spatially resolved biology requires representations that preserve biological neighborhood structure rather than only exact cross-modal correspondences. Existing histology--transcriptomics objectives can emphasize instance-level matching even when non-paired spots share molecular or spatial context. We introduce BioKERN, a multimodal spatial representation-learning framework that incorporates biological structure as an explicit, learnable...
-
04
A Geometric Theory of Robust Fairness Audits
Binita Maity
cs.LG
Neighborhood-based fairness audits evaluate individual fairness by comparing predictions among similar individuals in feature space. Despite their widespread use, little is known about the robustness of the auditing procedure itself. Because these audits rely on nearest neighbor relationships, small perturbations in feature space can alter local neighborhoods and produce different fairness assessments even when model predictions remain...
-
05
Effective Learning Rate Governs Loss Dynamics in Language Model Pretraining
Zihan Liu, Ruiheng Zheng, Shaobo Zhang, Changxin Tian, Kunlong Chen, Zhiqiang Zhang, Lei Wu
cs.LG
We uncover ELR collapse in language model pretraining: learning rate (LR) and parameter norm govern loss dynamics primarily through their ratio, the effective learning rate (ELR). When ELR is matched across runs, their loss trajectories collapse throughout training despite substantially different LRs and parameter norms. Across optimizers, architectures, datasets, and model scales, mean collapse errors are typically a few x 10^-3, below the...
-
06
MDTE: Minority-Aware Diffusion over Temporal Edge Events for Imbalanced Node Classification
Zhou Zelong, Zhang Tianming, Yang Zhengyi, Tang Yifu, Hou Chenyu, Cao Bin, Fan Jing
cs.LG
Class-imbalanced node classification on temporal graphs is challenging because majority-dominated temporal propagation progressively assimilates minority representations, while conventional node and neighborhood information provides insufficient discriminative evidence for minority classes. To address these issues, we propose MDTE, a minority-aware diffusion framework that reconstructs stable and discriminative temporal edge-event...
-
07
LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning
Xunkai Li, Zekai Chen, Zhengyu Wu, Henan Sun, Daohan Su, Guang Zeng, Hongchao Qin, Rong-Hua Li, Guoren Wang
cs.LG
Recently, the rapid advancement of multimodal domains has driven a data-centric paradigm shift in graph ML, transitioning from text-attributed to multimodal-attributed graphs. This advancement significantly enhances data representation and expands the scope of graph downstream tasks, such as modality-oriented tasks, thereby improving the practical utility of graph ML. Despite its promise, limitations exist in the current neural paradigms:(1)...
-
08
Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations
Sohini Gupta, Bahareh Tolooshams
cs.LG · cs.AI
Many disentanglement methods represent generative factors using Euclidean product coordinates, although the underlying factor spaces may wrap, collapse, or have position-dependent geometry. We introduce factor-space structure, combining factor domains, generator-induced identifications, and position-dependent scales to distinguish topologically equivalent spaces with different factor geometries. We show that statistically independent factors...
-
09
$(\text{DNN})^2$: Doubly Non-Negative Relaxations for Deep Neural Networks
Hanna Jiamei Zhang, Alan Papalia, Michael Everett, David M. Rosen
cs.LG · cs.RO · eess.SY
Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-conservative safety guarantees due to significant relaxation gaps. While the completely positive program (CPP) formulation closes this gap, it is NP-hard to solve. Its cheapest tractable relaxation, the doubly non-negative program (DNN), retains critical constraints as an SDP, but one whose...
-
10
Optimal Alternating Regret for Online Learning and Games
Yixin Tao, Weiqiang Zheng
cs.LG · cs.GT · stat.ML
We settle the minimax-optimal alternating regret, a regret notion motivated by alternating learning dynamics in games, for both online linear optimization (OLO) and online convex optimization (OCO). For OLO over the probability simplex $Δ_d$, we give an algorithm with $O(\log d)$ alternating regret that remains a constant for any time horizon $T$, and a matching lower bound. Our constant regret bound significantly improves previous results...
-
11
Parameter-Efficient Self-Supervised Adaptation for EEG-FM under Fixed Computational Budgets
Meghal Dani, Stefanie Liebe
cs.LG · cs.AI
EEG foundation models pretrained via self-supervised learning promise transferable representations, but their generalization remains limited, especially across diverse clinical datasets. Full fine-tuning is impractical for resource-constrained clinical settings due to high computational requirements. In this work, we investigate whether parameter-efficient self-supervised adaptation, updating only 9% of parameters suffices to align...
-
12
Enhancing Bayesian Optimization and Active Learning Through Kernel Diversity
Heng Zhang, Haotian Xiang, Qin Lu, Konstantinos D. Polyzos, Tara Javidi
cs.LG · cs.AI
Hyperparameter selection remains a key challenge in Bayesian optimization (BO) and Bayesian active learning (AL), as model misspecification can lead to suboptimal performance, while more accurate fully Bayesian treatments typically rely on computationally expensive MCMC sampling. This paper proposes a unified framework, KENDO (Kernel ENsemble Disagreement-aware Operator), that integrates Ensemble Gaussian Processes (EGP) with...
-
13
Constrained Hyperparameter Optimization for Streaming Data
Bruno Veloso, João Gama
cs.LG · cs.AI
Optimization of hyperparameters is a critical factor to obtain optimal model performance. While existing research has predominantly concentrated on batch-learning scenarios, addressing the complexities inherent in data streams presents a challenge. The deployment of sophisticated methodologies to manage data streams becomes highly important. Consequently, the capacity for self-adjusting hyperparameters during on-line learning phases emerges...
-
14
Parameter-Level Attribution of Symmetry in Trained Networks Though Parameter-Wise Functional Sensitivity
Alan Muriithi, Vedanta Thapar, Torben Berndt
cs.LG
When a network has learned a function with a known symmetry, can that symmetry be moved through the parametrisation---is there a motion in parameter space realising the group action in function space? We formulate this as a lifting problem for the realisation map $Φ:θ\mapsto f_θ$, and show that a smooth parameter-space action exists only if the tangent space to the function's symmetry orbit lies within the image of $\mathrm dΦ_θ$, whose...
-
15
Single State Update Predictive Coding training for Time Series Forecasting and Anomaly Detection
Matteo Cardoni, Sam Leroux
cs.LG · cs.NE
Predictive Coding (PC) is a neural learning paradigm that enables parallelizable neural network layer updates. However, the main bottleneck of PC Networks (PCN) is the sequential backwards error propagation. To tackle this, we introduce a training technique that pairs a Generative PCN with a support Encoding PCN. The two PCNs are trained in parallel to match their neural activations, without sequential propagation. We apply this to time...
-
16
On-policy Distillation with Verifiable Reward
Wenze Lin, Jiale Zhao, Xitai Jiang, Songde Rao, Yining Li, Shenzhi Wang, Bingxiang He, Gao Huang
cs.LG · cs.AI
Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted paradigms for post-training large language models. However, RLVR suffers from sparse task-level feedback, while OPD provides dense token-level guidance but ignores trajectory correctness, limiting its performance to that of the teacher. Combining them is a promising direction: OPD supplies dense supervisory signals, while RLVR...
-
17
A Multimodal Foundation Model for Longitudinal Patient Representation and Scalable Insight Generation in Oncology
Eugene Vorontsov, Yi Kan Wang, Alican Bozkurt, Adam Casson, Ludmila Tydlitatova, Michal Zelechowski, Ezra E. W....
cs.LG
Precision oncology necessitates a longitudinal model of patient state that captures cancer evolution and treatment over time, integrating multimodal observations. We introduce the oFM, a foundation model developed on a real-world oncology cohort of 1.67 million cancer patients that integrates clinical trajectories with DNA, RNA, and H&E pathology. Patient-level partitions were reserved for training, validation, and testing, with over one...
-
18
Data Leakage Inflates Generalizability of Power Outage Prediction Models
Yamil Essus, Ranga Raju Vatsavai, Benjamin Rachunok
cs.LG
Power outage prediction models are increasingly used in assessments of climate-driven infrastructure risk, yet current evaluation practices obscure whether these models generalize to the novel conditions such applications require. We identify three common methodological choices in power outage prediction models that influence their ability to generalize across spatial, temporal, and event-based settings. We compare the predictive performance...
-
19
Bandit Submodular Maximization under Matroid Constraints: Learning Compressed Exchange Policy
Zongqi Wan, Zhijie Zhang
cs.LG
We study adversarial bandit maximization of monotone submodular functions under a matroid constraint. For a rank-$k$ matroid on $n$ elements, we give a randomized oracle-polynomial algorithm that makes one feasible value query per round and has expected $(1-1/e)$-regret $\widetilde O(n^{1/3}k^{2/3}T^{2/3})$. This is the first sublinear-regret algorithm for adversarial bandit submodular maximization under general matroid constraints....
-
20
Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks
Yulong Dou, Han Wu, Guo Chen, Fangmao Ju, Zhiming Cui, Dinggang Shen
cs.LG · cs.AI
Electroencephalography (EEG) is a widely used window into human brain function, but most EEG models remain tied to a one-dataset-one-model supervised paradigm. Recent EEG foundation models offer a route toward reusable representations, but most remain reconstruction-centered, assuming that EEG content predictable from local context is necessarily transferable neural information. Here we present INCEPT, an invariance-oriented EEG foundation...
-
21
Delayed Optimizer-State Transport Shapes Short-Horizon Training Decisions
Jinhui Guo
cs.LG · physics.comp-ph
Adaptive optimizers retain gradient history in moment variables, allowing a local change in loss weighting to alter later updates. We examine whether this delayed transport is large enough to change prospective short-horizon decisions. On committed future-minibatch sequences, we differentiate eight-step AdamW trajectories through the complete model--optimizer state and select exposure-matched Math--Code loss schedules before independent...
-
22
IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents
Bo Ren, Yirong Mao, Yi Yang, Wenhui Que
cs.LG
Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information often unfolds over time rather than being fully specified at the initial prompt. Service agents make this challenge especially concrete: users may clarify or revise their goals, while tool responses provide information needed for subsequent decisions. Thus, a final...
-
23
Across the Loss Landscape with Progressive Growth
Paul Caillon, Christophe Cerisara, Alexandre Allauzen
cs.LG · cs.AI
Deep neural networks generalize well despite their highly nonconvex, overparameterized loss landscapes, a phenomenon often associated with the geometry of the minima found by stochastic optimization. We study how incremental grow-and-optimize strategies bias training toward flatter regions by viewing growth as progressive constraint relaxation. Starting from a low-dimensional submodel, we iteratively expand the trainable parameters by...
-
24
SeisMamba: Low-Latency Single-Station Seismic Magnitude Estimation for Spatially Distributed Earthquake Early Warning
Quenton Yeo, Zhaoge Bi, Linghan Huang, Luke Stephen Higgins, Flora Salim, Huaming Chen
cs.LG
Rapid earthquake magnitude estimation is central to earthquake early warning, yet many operational systems depend on dense regional seismic networks and region-specific calibration. This creates a spatial coverage barrier for high-risk areas with sparse sensing infrastructure. Single-station learning offers a lower-cost alternative, but existing models often face an accuracy--latency trade-off and may degrade under regional distribution...
-
25
FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment
Xitong Zeng, Zhaoge Bi, Yitian Yang, Huaming Chen, Quan Z. Sheng
cs.LG · cs.AI
Machine learning models are widely used in financial fraud and credit-risk detection, yet their adversarial robustness remains difficult to evaluate because financial tabular data involve domain-specific constraints, severe class imbalance, and asymmetric attacker capability. We argue that, in this setting, robustness is not only an attribute of the model, but also an attribute of the evaluation protocol. Different ways of enforcing...
-
26
Persistent Cross Entropy
Sijin Yeom, Jae-Hun Jung
cs.LG · cs.IT
Persistent entropy is the Shannon entropy of a persistence-based probability measure defined on a persistence diagram. However, its cross-entropy version is not naturally defined because two persistence diagrams generally have different event spaces. To bridge these event spaces, we combine a similarity function with persistence weighting to define an induced probability. The induced probability reflects information from one diagram on the...
-
27
From Numerical Simulators of PDEs to Neural Emulators and Back
Felix Koehler
cs.LG
Simulation is central to modern engineering and science, but the cost of numerical solvers for partial differential equations (PDEs) remains a bottleneck whenever fast or many-query evaluations are required. Neural emulators trained on solver-generated data promise significant speedups, yet they are usually framed as opaque alternatives to the very methods that produce their training signal. This thesis argues the two paradigms are more alike...
-
28
It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-dimensional output spaces
Leonhard F. Feiner, Manuel Nickel, Martin Menten, Laurin Lux, Rickmer Braren, Daniel Rueckert, Georgios Kaissis,...
cs.LG · cs.CV
Uncertainty Quantification (UQ) plays a vital role in enhancing the reliability of deep learning model predictions, especially in scenarios with high-dimensional output spaces. This paper addresses the dual nature of uncertainty -- aleatoric and epistemic -- focusing on their joint integration in high-dimensional regression tasks. For example, in applications like medical image segmentation or restoration, aleatoric uncertainty captures...
-
29
When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study
Mohit Singh Chauhan, Vipin Gyanchandani, Dylan Bouchard
cs.LG · cs.AI · cs.CL
Uncertainty quantification (UQ) methods are widely used for hallucination detection in large language models (LLMs) in closed-book settings where ground-truth evidence is unavailable at inference time. Prior work has proposed combining UQ signals via learned ensembles, but empirical investigations into the robustness of these ensembles are limited. We study a supervised ensembling framework that trains a classifier over heterogeneous UQ-based...
-
30
Where Entropy Is Measured Matters: Policy Geometry in Bounded Continuous-Control PPO
Yiyang He, Zhichun Zhou, Ziwei Wang, Tao Xue, Haolin Fei
cs.LG
Many continuous-control policies are optimized as unbounded Gaussians and then mapped into bounded actions. We show that where entropy is measured changes the policy geometry learned by proximal policy optimization (PPO). In an 80-muscle MyoLeg task, a clipped Gaussian executes 89.07% of actions within 5% of a bound. A same-state decomposition shows that this is not due to variance alone: setting variance to zero still leaves 83.83% of...
-
31
Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning
Hang Chen, Jiaying Zhu, Wenya Wang
cs.LG · cs.AI · cs.CL
Mechanistic Localization bridges mechanistic interpretability and post-training optimization by isolating critical parameters via interpretative approaches and then guiding parameter-efficient Supervised Fine-Tuning (SFT) in a ``locating-then-tuning'' paradigm. However, due to the retrospective nature of mechanistic interpretability, directly interpreting pre-SFT models introduces misleading conclusions. Specifically for novel tasks,...
-
32
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation
Zihao Wu, Hongyao Tang, Yi Ma, Huizhong Song, Pengyi Li, Yifu Yuan, Fei Ni, Jinyi Liu, Wei Wei, Jianrong Wang, Yan...
cs.LG
Massively parallel simulation changes the data regime in which off-policy reinforcement learning (RL) is trained, challenging stabilizers designed for data-limited replay. Through controlled experiments across eight benchmark families, we show that these stabilizers are data-regime-dependent: parameter normalization helps with narrow replay coverage but restricts value fitting when data are abundant, while clipped double-Q can be relaxed in...
-
33
Evaluating Deep Multivariate Imputation Models on Wearable Device Data
Skye Goodman, Roussel Desmond Nzoyem, Leandro Junges, Peter Kissack, Yasser Qureshi, Amberly Brigden, Jeff Clark,...
cs.LG · cs.AI · q-bio.QM
Wearable device data enables continuous health monitoring, but suffers from structured missingness: features sharing a physical sensor drop out together. Deep imputation methods such as BRITS and SAITS have seen limited evaluation on multimodal physiological data under realistic missingness, and existing benchmarks use random-point holdout protocols that incorrectly assume missingness is independent across features and time. Using data from a...
-
34
Joint Distribution Alignment for Universal Domain Adaptation
Shizhe Li, Hongshan Pu, Mengying Xie, Yi Xiang, Xiaowei Yang
cs.LG · cs.CV
Unsupervised domain adaptation (UDA) has been widely concerned in the fields of machine learning, pattern recognition, and computer vision. Traditional UDA learning usually assumes that the label spaces of the source and target domains are exactly the same and only needs to solve the problem of sample distribution drift existing between two domains. However, in real world applications, the label spaces between two domains may be different. In...
-
35
Equivariant Covariance Tensors: Guaranteed SPD Uncertainty for Tensor-Valued Geometric Learning
Ruihan Liu, Yu Ji, Jianbo Yu, Shifu Yan, Qingchao Jiang
cs.LG · cs.AI
Tensor-valued prediction is fundamental to geometric deep learning, yet uncertainty quantification (UQ) for such outputs remains an open challenge. While E(3)-equivariant neural networks excel at point estimates, they lack rigorous confidence measures. We focus on symmetric rank-2 tensor prediction, where the target has six Kelvin--Mandel coordinates and full uncertainty is represented by a $6\times6$ covariance matrix. We introduce a...
-
36
When Does Self-Supervised Pretraining Help Tabular Models? A Study of Label Scarcity and Missing Data
Sahand Mazrouei
cs.LG
Self-supervised learning (SSL) has emerged as a promising approach for tabular data, yet its efficacy under extreme label scarcity and test-time missingness remains under-explored. In this paper, we evaluate a mask-and-recover SSL pretraining objective against training from scratch and classical baselines across 14 diverse classification tasks. First, while SSL outperforms training from scratch on average and remains competitive with...
-
37
A Structural FHMM for Interpretable Disease Trajectories in T2DM
Alessandro Mari, Ekaterina Krymova, Guillaume Obozinski, Maria Luisa Marques de Sa Faquetti, Adrian Martinez de la...
cs.LG
In this work, we propose a structural variant of the Factorial Hidden Markov Model (FHMM) for the analysis of disease trajectories in patients with Type 2 diabetes mellitus (T2DM). The model represents a patient's latent health state as a combination of multiple independent, simultaneously evolving components, associated with comorbidities and lab results. This structured latent representation facilitates the identification of clinically...
-
38
Causal Analysis for Time Series Foundation Models
Mathis Jander, Wouter van Heeswijk, Martijn Mes
cs.LG
Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one to one-to-many. This shift introduces concentration risk as many, potentially high-risk, forecasting applications are exposed to the same biases and failure modes of a single time series foundation model. At the same time, this centralization allows for economies of scale in model development...
-
39
Contrastive Branch Policy Optimization
Ying Wang, Changlin Qiu, Bang Lin, Linbo Jin, Wen Jiang, Zhe Sun, Jingli Yang
cs.LG · cs.AI
Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn interaction with external tools, yet its sparse outcome rewards provide no signal for identifying which intermediate decisions are responsible for success. Branch sampling induces local comparisons among alternative continuations, but existing methods tend to conflate two distinct problems: allocating a fixed rollout budget and translating branch...
-
40
A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm
Duy Hoang, Bastien Berret, Olivier Bruneau, Laurent Fribourg
cs.LG
Training neural networks requires balancing the trade-off between fitting the training data and achieving robust performance on unseen inputs. This ability, commonly referred to as generalizability, is determined by the gap between the empirical risk on the training set (``empirical loss'') and the expected risk over the data distribution (``generalization error''). Existing approaches typically estimate the generalization error numerically,...
-
41
PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization
Yunxiao Luo, Siyuan Wang, Ben Chen, Chenyi Lei
cs.LG
Semantic identifiers (SIDs) represent entities as hierarchical token sequences for generative retrieval and recommendation. Residual-quantization tokenizers construct these sequences by selecting a codeword at each level and passing a residual to the next. We view this process as progressive commonality removal: each token captures a component shared within its group, while later tokens should model the remaining differences. This view...
-
42
From Relaxed Indexability to Exact Indexability: A $t$-Step Approach for Partially Observable Restless Bandits
Qizhen Jia, Keqin Liu
cs.LG · math.OC
Whittle index policies offer a scalable method for restless multi-armed bandits, but under partial observability even determining the indifference subsidy at a single belief requires solving an infinite-horizon belief-state problem with no closed-form value function. Liu [10] addresses this difficulty by linearizing the unknown decision boundary, leading to a linear system and a closed-form approximate Whittle index. However, the resulting...
-
43
Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation
Claire Chen, Shuze Daniel Liu, Licheng Luo, Rohan Chandra, Nan Jiang, Shangtong Zhang
cs.LG · stat.ML
In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate this issue, behavior policy search has been proposed to learn data-collecting policies tailored to reduce online evaluation variance. However, these approaches do not account for uncertainties in the transition functions. In practice, simulator transitions often differ from the real world due...
-
44
Steering Recurrent Reasoners at Inference Time with Readout Feedback
Shunsuke Kamiya, Masanori Koyama, Seongcheol Jeong, Fumiya Uchiyama, Kenji Kubo, Kohei Hayashi, Masahiro Suzuki,...
cs.LG
Recurrent models, which repeatedly update latent states with shared computation blocks, have emerged as powerful architectures for solving complex reasoning tasks. Existing inference-time methods scale computation by running more steps or sampling more trajectories, but ignore information revealed within each trajectory. Here we show that recurrent models can be improved at inference time by using their own readout probabilities to steer...
-
45
From Gradient-Boosted Trees to Deep Recommenders: Practical Lessons from Migrating a Production Customer Support Recommender
Sonia Sharma, Jeyendran Balakrishnan, Shreya Rajpal, Swapnil Parekh, Nagaraj Janardhana, Andrew Mattarella-Micke
cs.LG · cs.AI
Product catalogs in fast-moving service businesses are shifting from static, independently priced SKUs toward dynamically bundled, discount-coupled offerings--a shift that strains the tree-based classifiers traditionally preferred for sparse and highly imbalanced data. These classifiers assume a fixed, slowly changing label space and struggle to incorporate multimodal signals such as tabular data and transcripts. We present the migration of a...
-
46
A mesh-free multiresolution deep energy method with phase-field modeling of brittle fracture
Han Zhang, Mehrisadat Makki Alamdari, Babak Shahbodagh, Mohammad Vahab, Cosmin Anitescu, Timon Rabczuk, Elena Atroshchenko
cs.LG · math.NA
Phase-field modeling of brittle fracture removes the need to track cracks explicitly by recasting their evolution as the minimization of an energy functional. In return it requires a discretization dense enough to resolve a localization band whose width is set by a regularization length and whose path is not known in advance. We propose a mesh-free discretization in which a single neural network represents the displacement and phase fields...
-
47
Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection
Jungwook Seo, Sangwon Son, Minjeong Kim, Seungmin Han, Seojin Yoo, Sungyong Baik
cs.LG · cs.AI
Time-series anomalies can appear not only as pointwise deviations but also as changes in recurring temporal structure, such as shifted periodicity or localized oscillatory fluctuations. However, existing LLM-based time-series anomaly detection methods mainly expose time-domain evidence through indexed values, plots, or de-seasonalized representations, leaving spectral structure implicit. We propose an evidence-augmented zero-shot TSAD...
-
48
The Sharp Tail of Uniform Stability
Pahan Dewasurendra
cs.LG
Uniform stability controls how much one training example can change the loss at any test point. A new logarithmic-free upper bound shows that a $γ$-uniformly stable algorithm with loss in $[0,L]$ has generalization gap at most $O \left(γ\log(1/δ) +L\sqrt{\frac{\log(1/δ)}{n}}\right)$ with probability $1-δ$. Whether an actual bounded-loss learning algorithm can realize the linear dependence on $\log(1/δ)$ has remained open. The known...
-
49
Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents
Nadeem Shaikh
cs.LG · cs.AI · stat.ML
Current LLM agent systems decide delegation before reasoning begins (a router picks a model) or after a response is complete (a verifier scores it and may retry). We study a third regime: an agent that recognises, during its own reasoning, that it is unlikely to succeed and transfers control to a stronger model. We formulate intra-generation delegation as a Bayesian optimal-stopping problem over a learned competence posterior -- an online...
-
50
A Feature-Major Codebook for Memory-Efficient Sparse-Binary Self-Organizing Maps: Scaling a MEDLINE Atlas to 1.05 Million Neurons on a Single Consumer GPU
Andrew James Amos
cs.LG · cs.DC
A self-organising map turns a large corpus into a browsable two-dimensional atlas, but building one at MEDLINE scale has been impractical: the best-matching-unit (BMU) search that dominates training is bound by the bandwidth needed to read the codebook every epoch. I show that this bottleneck is largely an artefact of codebook layout. Storing it feature-major with each feature's weights contiguous, W[v.M+i], recasts the search as a tiled...
-
51
Mechanistic Circuit Identification for Controllable Data Generation
Nakyung Lee, Sangwoo Hong, Jungwoo Lee
cs.LG · cs.AI · cs.CL
While recent advances in data synthesis aim to curate high-quality datasets, most generation pipelines still rely on heuristic prompt-based control. This black-box paradigm provides limited insight into how individual samples interact with a model's underlying learning dynamics. To bridge this gap, we propose a circuit-grounded framework that connects training-dynamics-based data valuation with mechanistic interpretability (MI). Specifically,...
-
52
PhysicsBench: A Unified Leaderboard for Generative and Predictive Models in Engineering Design and Simulation
Sang Won Lee, Hyogu Jeong, Namwoo Kang
cs.LG · cs.CE
Generative and predictive artificial intelligence models are increasingly used to generate geometry and to predict physical fields and scalar quantities in engineering design and simulation. Yet these models are typically evaluated in isolation, on academic datasets at unconstrained scales, with inconsistent metrics and procedures. We present PhysicsBench, a unified benchmark and leaderboard that evaluates generative and predictive models...
-
53
ALPHABET: A Laplace-Pole History Aggregator with Banked Exponential Transport
Daehwa Ko, JaeHyeon Kim, Oh Seong Kwon, Jay Hoon Jung
cs.LG
Can a sequence model remain competitive with only a few thousand parameters and an explicitly auditable prediction interface? We introduce ALPHABET, a compact linear-time model that compresses temporal history into stable complex pole modes: a direct bank synthesizes its modal states back into the feature trajectory, an independent cascaded bank analyzes the transformed trajectory without resynthesis, and an affine head reads only modal...
-
54
Physics-Integrated Operator Learning via Gaussian Splatting Representations
Jihao Zhang, Junyi Guo, Jian-Xun Wang
cs.LG
Neural operators provide efficient surrogates for spatiotemporal PDE systems, but purely data-driven formulations often accumulate substantial errors during long-horizon autoregressive prediction and may fail to exploit available governing-equation structure. Existing approaches incorporate physics primarily through residual-based training objectives or PDE-specific architectural constraints, which can introduce optimization difficulties or...
-
55
XP-JEPA: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics
Kehan Wen, Ziming Li, Siyuan Luo, Fan Shi
cs.LG
Latent world models plan by predicting how candidate actions transform learned representations. In self-predictive models, however, the encoder and predictor are optimized jointly and can co-adapt to latent transitions that are easy to predict but only weakly constrained by the physical evolution of the scene. We introduce the cross-predictive JEPA (XP-JEPA), which grounds visual latent dynamics in privileged physical trajectories. XP-JEPA...
-
56
PinSieve: Production Selective VLM Serving and a Governed Memory Flywheel for Enterprise Content-Quality Triage
Chuqing Gao, Yuanfang Song, Jonathan Zhang, Yifan Wu, Vishwakarma Singh, Qinglong Zeng, Andrey Gusev
cs.LG
Enterprise AI agents in production often need to be bounded, stateful, observable, and governable rather than fully autonomous. We present PinSieve, a production case study in a large-scale content-quality pipeline. Its deployed component is a selective vision-language-model (VLM) Serving Agent that operates only on the grey-zone slice left unresolved by lightweight upstream models, exposes a scalar routing score online, and preserves...
-
57
ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning
Juntao Fang, Shifeng Xie, Ruichu Cai, Shengji Zheng, Zijian Li, Keli Zhang, Lujia Pan, Themis Palpanas, Zhifeng Hao
cs.LG · cs.AI · stat.ML
Time series classification underpins applications in healthcare, sensing, and industrial monitoring. Although time series foundation models support forecasting and transferable representation learning, classification still typically requires fitting a task-specific classifier on each target dataset, while individual channels of multivariate inputs are often encoded independently. We introduce ChorusTIC, a classification-native foundation...
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.