cs.LG · 2026-06-02 · No. 13
Machine Learning, 2026-06-02.
59 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
59 entries-
01
IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning
Farhin Farhad Riya, Olivera Kotevska, Jinyuan Stella Sun
cs.LG · cs.CR · cs.DC
Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity. In practice, many HDP-FL systems employ $\varepsilon$-aware server aggregation to improve model utility by re-weighting client updates according to their declared privacy budgets. However, gradient updates in FL retain structural patterns induced by...
-
02
Drifting Preference Optimization for One-Step Generative Models
Zhou Jiang, Yandong Wen, Zhen Liu
cs.LG · cs.CV
One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step...
-
03
A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution
Yeganeh Marghi, Kelly Jin, Uygar Sümbül
cs.LG
Optimal transport (OT) provides a principled framework for mapping between probability distributions. Despite extensive progress, applying OT to large-scale data remains computationally demanding, and the resulting pointwise transport plans are often difficult to interpret. We introduce Optimal Mixture Transport (OMT), a scalable framework that shifts the transport paradigm from individual samples to mixtures of subpopulations, reformulating...
-
04
Expressivity of congruence-based architectures for DNNs on positive-definite matrices
Antonin Oswald, Estelle Massart
cs.LG
This work studies neural architectures for classifying symmetric positive-definite matrices, focusing on congruence-like layers, in which the input matrix is multiplied on the left and right by a (possibly rectangular) weight matrix $W$ and its transpose. Such layers lie at the core of the celebrated SPDNet and have also been employed independently for dimensionality reduction on positive-definite data. We show that the (semi)-orthogonality...
-
05
Speculative Sampling For Faster Molecular Dynamics
Arthur Kosmala, Stephan Günnemann, Meng Gao, Brandon Wood
cs.LG · cond-mat.mtrl-sci · physics.chem-ph · physics.comp-ph · stat.CO
Molecular dynamics (MD) is a key tool for simulating the dynamical behavior of atomic systems. However, MD is inherently serial, which makes it difficult to increase single-system throughput with concurrent compute. To address this, we introduce Langevin Speculative Dynamics (LSD), a distributed and model-agnostic speculative sampler for accelerating MD without adding relative error. Inspired by speculative methods in language and diffusion...
-
06
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Mind Lab, :, Song Cao, Vic Cao, Kaijie Chen, Bunny Fan, Hera Feng, Huan Feng, Arthur Fu, Jun Gao, Hongquan Gu, Aaron...
cs.LG · cs.CL
Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state on top of strong shared foundation models. In this framing, the base model provides shared competence while adapters carry instance-specific behavior such as preferences, skills, tool habits, and memory-like updates. We organize the problem around three scaling...
-
07
A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL
Lei Yang, Siyu Ding, Deyi Xiong
cs.LG · cs.CL
Reinforcement learning (RL) post-training improves large language models (LLMs) on individual domains such as mathematical reasoning, code generation, question answering, and creative writing (CW), but training on one domain often degrades performance on others. Existing explanations based on catastrophic forgetting or global gradient conflict are incomplete: substantial interference can occur even when full-model gradients are nearly...
-
08
Policy and World Modeling Co-Training for Language Agents
Ning Lu, Baijiong Lin, Shengcai Liu, Jiahao Wu, Haoze Lv, Yanbin Wei, Lingting Zhu, Shengju Qian, Xin Wang,...
cs.LG · cs.AI
Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do to the environment. World modeling (WM) can fill this gap, yet existing approaches often require separate simulators, extra training stages, or additional inference-time computation. We observe that on-policy RL rollouts already contain the needed signal: each...
-
09
TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks
Andrej Tschalzev, Nick Erickson, Yuyang Wang, Huzefa Rangwala, Stefan Lüdtke, Heiner Stuckenschmidt, Christian Bartelt
cs.LG
Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures. At the same time, feature engineering remains a critical yet underexplored component of real-world modeling pipelines that is entirely absent from modern benchmarks, which creates an unquantified evaluation gap. In this work, we introduce TabPrep, a lightweight preprocessing pipeline composed of feature generators that are carefully...
-
10
When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures
Yongzhong Xu
cs.LG · cs.AI
We track the developmental trajectory of attention-head circuit formation across three 1B-class language models spanning two architecture families (dense transformer, mixture-of-experts) and two pretraining corpora (The Pile, DCLM): Pythia 1B, OLMo 1B-0724-hf, and OLMoE 1B-7B-0924. At each of 10 log-spaced revisions per model -- 30 mechanistic-interpretability runs in total -- we apply a participation-ratio (PR) spectral signal and an...
-
11
FOAM: Frequency and Operator Error-Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
Kyunghun Nam, Sumyeong Ahn
cs.LG · cs.AI
Shampoo is attracting considerable attention for its superior performance on large-scale optimization benchmarks; yet it faces a significant practical bottleneck: the prohibitive computational overhead of matrix inversion. To mitigate this, practitioners typically rely on stale preconditioner updates, creating a fundamental trade-off between computational efficiency and optimization fidelity. In this work, we provide a theoretical study of...
-
12
Minimax-Optimal Policy Regret in Partially Observable Markov Games
Raman Arora
cs.LG · stat.ML
We study sequential decision-making in partially observable environments against strategic, adaptive opponents, modeled as partially observable Markov games (POMGs). The central challenge is to learn latent dynamics from partial observations while facing an adversary whose behavior depends on the learner's strategy, making standard regret notions inadequate. We prove that an epoch-based optimistic maximum-likelihood algorithm achieves...
-
13
Local Preferential Bayesian Optimization
Johanna Menn, Miriam Kober, Paul Brunzema, David Stenger, Sebastian Trimpe
cs.LG · stat.ML
Bayesian optimization (BO) is a popular and effective approach for tuning expensive, noisy experiments, but requires the formulation of an explicit objective function. Preferential BO (PBO) removes this requirement by learning from pairwise human feedback, yet existing methods struggle to efficiently optimize beyond low- and medium-dimensional problems due to their global search approaches. We address this limitation by developing a family of...
-
14
Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
Tim Nielen, Sameer Ambekar, Johannes Kiechle, Daniel M. Lang, Julia A. Schnabel
cs.LG · cs.CV
Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood. In this work, we show that distribution shifts can cause feature clusters corresponding to distinct classes in the model's representation space to merge, while the decision boundary remains fixed. This induces a systematic skew in the predicted class distribution, referred to as prediction bias....
-
15
Riemannian Gradient Descent for Low-Rank Architectures
Nicholas Knight
cs.LG
We explore Riemannian optimization techniques for rank-factored matrix parameters, targeting contemporary deep learning applications. We examine ten points in the algorithm design space: two geometries for rank-$r$ matrices, three geometries for rank-$r$ partial isometries, and block-matrix variants of these five, where factors are shared across block-rows and block-columns. We apply our methods to the multihead attention parameters in small...
-
16
Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment
Ran Liu, Min Yu, Mingqi Liu, Jianguo Jiang, Gang Li, Rongsheng Li, Ning Li, Zhen Xu, Weiqing Huang, Ming Liu
cs.LG · cs.AI
In dynamic environments, large language models need to keep adapting to new tasks, but continual learning often suffers from forgetting, limited transfer, and vulnerability to adversarial perturbations. To address this, we present AdvCL, which repurposes adversarial perturbations as a geometric control signal for stable continual adaptation. AdvCL combines three plug-in modules: Intra-Smooth promotes local smoothness via small adversarial...
-
17
Measurement Geometry and Design for Trustworthy Generative Inverse Problems
Pengfei Jin, Na Li, Quanzheng Li
cs.LG · cs.CV
Generative models are increasingly used as priors for inverse problems, but their ability to produce realistic images creates a basic trust problem: a plausible reconstruction may be supported by the measurements, or it may be filled in by the prior along unobserved directions. This distinction is especially important in medical imaging, where acquisition operators are designed under scan-time, dose, and calibration constraints. We study...
-
18
Regularized Large Neighborhood Search
Germain Vivier-Ardisson, Laurent Demonet, Axel Parmentier, Mathieu Blondel
cs.LG
Operations research practitioners typically tackle NP-hard combinatorial problems using large neighborhood search (LNS), a scalable heuristic that iteratively refines a current solution by locally re-optimizing subsets of its variables. In contrast, most existing approaches for integrating combinatorial optimization layers into neural networks still assume access to an exact global solution, which is computationally intractable. We bridge...
-
19
Massive Spikes in LLMs are Bias Vectors: Mechanistic Uncovering and Spike-Free Quantization
Yung-Chin Chen, Chung Peng Lee, Ze-Wei Liou, Naveen Verma
cs.LG
Massive activation spikes in Large Language Models (LLMs) severely degrade quantization by stretching dynamic ranges. While prior hypotheses characterize these as high-level scalar biases, we argue that they are merely the scalar intermediates of rigid, structural vector biases in the spike-carrying tokens. We show that these tokens converge to constant vectors after normalization that drive the attention sink and value-state drain...
-
20
CityTrajBench: A Unified Benchmark for City-Scale Vehicle Trajectory Generation
Shibo Zhu, Xiaodan Shi, Dayin Chen, Yuntian Chen, Haoran Zhang, Tianhao Wu, Jinyue Yan
cs.LG · cs.AI
Urban trajectory generation is a fundamental task for transportation simulation, urban planning, and mobility analytics. However, systematic comparison across trajectory generation methods remains difficult because existing studies often rely on different datasets, preprocessing pipelines, trajectory representations, and evaluation metrics. This fragmentation makes it unclear whether reported performance differences arise from the generation...
-
21
A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs
Nicolas Stalder, Benjamin F. Grewe, Matteo Saponati, Pau Vilimelis Aceituno
cs.LG · cs.CV
The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment. Existing techniques to enhance deep network robustness rely on adversarial training, an approach that is powerful but computationally intensive and typically tailored to specific attack types. To address these limitations, existing works have explored techniques such as adding gaussian noise or filtering images, both of...
-
22
ArrythML: An Autoencoder-Based TinyML Approach for On-Device Arrhythmia Detection on Resource-Constrained Embedded Systems
Nagarajan S, Kurian Polachan
cs.LG
Our work presents a method for ECG segmentation and arrhythmia detection using Tiny Machine Learning (TinyML) models for real-time, on-device inference on resource-constrained embedded systems. We develop INT8 quantized autoencoder-based TinyML models with minimal layers and parameters for embedded deployment. These models are evaluated using a custom dataset derived from the MIT-BIH Arrhythmia Database and validated in both PC-based...
-
23
BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers
Justin Deschenaux, Caglar Gulcehre
cs.LG
Is the uniform-state diffusion framework a more powerful paradigm for discrete diffusion? Recent studies indicate that this may be the case. In combination with predictor-corrector samplers, uniform-state diffusion models (USDMs) produce samples of higher-quality than masked diffusion models (MDMs), and USDMs equal or outperform MDMs in downstream tasks, even though they exhibit greater perplexity. Two issues remain unresolved. First,...
-
24
Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation
Shucheng Li, Iolo Jones, Alexander Tong, Michael M. Bronstein
cs.LG
Distribution Matching Distillation (DMD) compresses pretrained diffusion models into efficient few-step generators by aligning their noised distributions across all scales. In principle, such distribution-level supervision remains agnostic to specific noise-data pairings of the teacher; this provides the student the freedom to remap latent noise, a behavior consistently observed in low-dimensional settings. Surprisingly, we find that in...
-
25
A Doeblin-Anchored Contrastive Chart for Learning Markov Transition Kernels
Ao Xu
cs.LG
Learning a Markov transition model is not merely conditional density estimation: the learned object must be a valid transition kernel before it is iterated in downstream dynamics. This paper introduces a Doeblin-anchored contrastive chart, a statistical-to-dynamical coordinate framework for learning transition kernels from contrastive objectives. Given a restart law and an anchor strength, the chart mixes the target transition with the...
-
26
Network Learning with Semi-relaxed Gromov-Wasserstein
Charles Dufour, Ulysse Naepels, Leonardo V. Santoro
cs.LG · math.ST · stat.ME
Estimating the generative mechanism of large-scale networks is a fundamental challenge in statistical machine learning. It requires the identification of the latent connectivity structure, which is in general an NP-hard combinatorial problem due to the absence of canonical node labels. We address this challenge by allowing for probabilistic couplings, thereby relaxing the assignment problem. Our estimation framework can be formulated as a...
-
27
Faster Synchronous On-Policy RL via Straggler-Aware Group Sizing
Azal Ahmad Khan, Ammar Ahmed, Zeshan Fayyaz, Sheng Di, Mingyi Hong, Ali Anwar
cs.LG · cs.AI
Synchronous reinforcement learning methods such as Group Relative Policy Optimization (GRPO) provide stable and reproducible on-policy training, but they are highly vulnerable to stragglers, a single unusually long rollout can delay reward computation and parameter updates for the entire group. This problem becomes more severe as group size increases, creating a tension between the benefits of larger groups and the wall-clock cost of...
-
28
Model Multiplicity and Predictive Arbitrariness in Recidivism Risk Assessment
Ashwin Singh, Carlos Castillo
cs.LG · cs.CY
Prediction tasks over individual futures, which are inherently noisy, often admit multiple similarly accurate models. When these models produce different predictions for the same individual, they raise concerns of arbitrariness in decision-making. How severe can this arbitrariness be, in theory and in practice? How can it be resolved to support high-stakes risk assessment? We address these questions through a study of a machine learning-based...
-
29
Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters
cs.LG
Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation. Reinforcement learning (RL) can be used as a means to finetune these policies further using additional experience. An open question is whether RL is more sample-efficient than collecting more human demonstrations. Prior work has finetuned...
-
30
On the Generalization in Topology Optimization via Sensitivity-Conditioned Bernoulli Flow Matching
Mohammad Rashed, Duarte F. Valoroso Madeira, Babak Gholami, Caglar Guerbuez, Yunjia Yang, Nils Thuerey
cs.LG · cs.AI · cs.CE
Surrogate models for topology optimization (TO) exhibit highly variable out-of-distribution (OOD) generalization under distribution shifts such as changing loads or boundary conditions, yet the source of this variability remains unclear. We hypothesize that OOD performance is governed by how much information the conditioning signal preserves about the adjoint sensitivity (reduced gradient) that drives classical TO. Modeling the TO pipeline as...
-
31
Low-Pass Flow Matching
Francesco M. Ruscio, T. Konstantin Rusch
cs.LG
Flow Matching typically relies on white noise sources, a choice often misaligned with the power spectra of natural data, which tend to decay with frequency. To address this, we introduce Low-Pass Flow Matching, a variant of Flow Matching based on an operator-modulated interpolant. This formulation induces a time-varying spectral bias that transitions from the source spectrum to a frequency-decaying bias as the path approaches the data. We...
-
32
Closing the Alignment-Maturity Gap in Federated Prototype Learning
Mario Casado-Diez, Alejandro Dopico-Castro, Verónica Bolón-Canedo, Bertha Guijarro-Berdiñas
cs.LG · cs.CV
Learning discriminative visual representations from distributed, heterogeneous data is a fundamental challenge in Federated Learning (FL). Prototype-based methods address statistical heterogeneity by sharing class-level representations across clients but create a distance-dependent gradient pressure that is particularly severe during early training rounds: alignment pressure applied to immature global prototypes, aggregated from noisy local...
-
33
EEG-FuseFormer: A Transformer-Driven Feature Fusion Framework for Seizure Onset Prediction
Vigneshwar Hariharan, Chithra Reghuvaran, Arlene John, Nhat Pham, Omer Rana, Deepu John, Ganesh Neelakanta Iyer
cs.LG
Epilepsy is one of the most common neurological disorders globally, characterized by recurring seizures and significantly impacting the quality of life. Despite advancements in diagnostic techniques, the mitigation of risks faced by epilepsy patients remains challenging due to the unpredictability of seizure events. An accurate forecast of seizure onset helps to reduce risks in epilepsy patients. In this paper, we propose EEG-FuseFormer, a...
-
34
Hybrid Neural Ordinary Differential Equations for Data-Efficient Polymerization Modeling with Incomplete Kinetics
Marah Almanasreh, Alexander Mitsos, Eike Cramer
cs.LG
Accurate prediction of polymerization dynamics is essential for process design, control, and optimization. Yet, purely mechanistic models require labor-intensive parameterization of partially characterized kinetics, while purely data-driven models demand large, diverse datasets that are costly to obtain, particularly in early-design stages. We propose a hybrid Neural Ordinary Differential Equation (NODE) framework for data-efficient modeling...
-
35
TimeBlocks: Foundational and Continual Time-Series Blockbase -- Extended Version
David Campos, Bin Yang, Tung Kieu, Lei Chen, Chenjuan Guo, Christian S. Jensen
cs.LG · cs.DB
The ongoing digitization has led to a proliferation of time-series data streams that monitor a variety of processes, from which valuable insights may be obtained. Further, the emergence of successful foundational language models begs the question of whether it is possible to achieve time-series models with the foundational properties of handling multiple tasks, while being sufficiently lightweight to allow real-time data stream processing....
-
36
VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting
Xudong Zhang, Jierui Lei, Jiacheng Li, Lingdong Shen, Jian Cui, Haina Tang
cs.LG · cs.AI
Out of distribution (OOD) events in multivariate time series forecasting are rare but often dominate real world risk, making average case forecasting insufficient for reliable deployment. Under standard average risk training on mixed ID/OOD distributions, optimization signals from rare OOD events can be overwhelmed by frequent in distribution (ID) patterns, so strong benchmark accuracy may not translate into reliability under high impact...
-
37
Edge-aware Decoding for Neural Asymmetric Routing
Li Liang, Jinbiao Chen, Zizhen Zhang
cs.LG
Neural asymmetric routing models increasingly encode directionality through matrix representations and asymmetry-aware attention. The final routing action, however, is not a node in isolation but a directed transition chosen under the current partial route. This creates a representation--decision mismatch: pairwise cost information may be encoded upstream while the final candidate logit is still largely parameterized as context--node...
-
38
Rethinking Evaluation Paradigms in IBP-based Certified Training
Konstantin Kaulen, Hadar Shavit, Holger H. Hoos
cs.LG · cs.AI · cs.CV
Deep neural networks achieve strong performance on many supervised learning tasks but remain vulnerable to adversarial perturbations. Neural network verification provides mathematically rigorous robustness guarantees, yet at substantial computational cost. To mitigate this, certified training techniques optimise for verifiable robustness during training, typically inducing a trade-off between natural and certified accuracy controlled by...
-
39
Variational Learning for Insertion-based Generation
Yangtian Zhang, Zhe Wang, Arthur Gretton, Rex Ying, David van Dijk, Michalis K. Titsias, Jiaxin Shi
cs.LG · cs.AI
Non-monotonic sequence generation methods, such as masked diffusion models, provide a flexible alternative to left-to-right autoregressive modeling by allowing tokens to be generated in non-fixed and prescribed orders. Despite their practical advantages, most existing non-monotonic models are order-agnostic and rely on a fixed-length grid, limiting their ability to support variable-length generation and adaptive insertion order. In this work,...
-
40
How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
Jiangwei Chen, Xinyuan Niu, Rachael Hwee Ling Sim, Zhengyuan Liu, Nancy F. Chen, Bryan Kian Hsiang Low
cs.LG · cs.AI
Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the model performance on the remaining retain data. Existing unlearning algorithms, such as optimizing a weighted combination of losses, have tried to achieve these objectives of improving forget quality and maintaining retain utility. However, they do not guarantee that these objectives can be improved...
-
41
When Tabular Foundation Models Transfer Across Modalities: A Systematic Evaluation Across 95 Datasets, 7 Modalities, and Two Regimes
Julien Lafrance
cs.LG · stat.ML
We present a single classification pipeline that combines an Equiangular Tight Frame (ETF) preprocessing stage with a tabular foundation model for in-context inference, applied identically across modalities once data is mapped to fixed vector representations. We evaluate it on 95 datasets spanning seven signal modalities -- vision, audio, speech, text, molecular, time-series, and tabular. The main methodological contribution is to fix the...
-
42
Beyond $\ell_2$-norm and $\ell_\infty$-norm: A Curvature-Inspired $\ell_p$-Norm Scheme for Deep Neural Networks
Jianhao Xu, Zhuang Yang
cs.LG
The existing optimizers for deep neural networks (DNNs) typically rely on either the $\ell_2$ norm or the $\ell_\infty$ norm, resulting in optimizers that do not adapt well to substantial changes in curvature across parameter dimensions. Generally, the training process of DNNs often exhibits strong curvature anisotropy in the early period, whereas in the later period, the training process of DNNs tends to move toward flatter regions with...
-
43
Planar Symmetric Pattern Generation
Ning Lin, Luxi Chen, Huaguan Chen, Jiacheng Cen, Chongxuan Li, Wenbing Huang, Hao Sun
cs.LG
Generating objects with specific symmetries is essential in various real-world scenarios. However, adapting existing 2D continuous representations to enforce planar group symmetry remains a challenge, as the transformation of non-reflective group elements may disrupt continuity. To overcome this limitation, we propose a symmetrization framework for arbitrary planar groups. Our method transforms any 2D continuous representation into a...
-
44
Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design
Michał Brzozowski, Neo Christopher Chung
cs.LG
Dictionary learning with sparse autoencoders (SAEs) produces overcomplete bases from neural network activations that are often interpretable and reduces polysemanticity. However, features from SAEs vary substantially across random seeds -- a problem known as instability. Archetypal SAEs (Fel et al., 2025) were proposed as a general dictionary-learning intervention for more reliable concept extraction, and report more stable dictionaries at...
-
45
Realistic noise synthesis reduces bias and improves tissue microstructure estimation with supervised machine learning
Bradley G. Karat, Maëliss Jallais, Ali R. Khan, Santiago Aja-Fernández, Jelle Veraart, Marco Palombo
cs.LG · physics.med-ph
Diffusion MRI enables non-invasive probing of tissue microstructure, but accurate parameter estimation is challenged by noise-related effects. In supervised machine learning frameworks trained on simulated data, discrepancies between the noise characteristics of simulated and acquired signals introduce a form of covariate shift, whereby the input signal distribution differs between training and inference. We investigated the impact of this...
-
46
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai, Wenlin Yao, Hao Cheng, Baolin Peng, Huan Zhang, Tong Zhang, Jianfeng Gao
cs.LG · cs.AI · cs.CL · cs.CV
Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, while open agents still depend heavily on supervised post-training over large collections of curated web trajectories. This dependence creates a major scalability bottleneck: high-quality demonstrations are expensive to collect,...
-
47
Evaluating Real-World Generalizability of Algorithm Selection Models
Gjorgjina Cenikj, Jakub Kudela, Eva Tuba, Tome Eftimov
cs.LG
Algorithm Selection (AS) aims to automatically identify the most suitable optimization algorithm for a given problem instance by leveraging measurable problem characteristics and historical performance data. In this study, we investigate the generalization ability of AS models across both synthetic and real-world optimization landscapes. We consider two widely used academic benchmark suites (BBOB and CEC) and two real-world problem sets...
-
48
Why Do Time Series Models Need Long Context Windows?
Luca Butera, Giovanni De Felice, Andrea Cini, Cesare Alippi
cs.LG · cs.AI
Modern deep learning models for forecasting groups of time series rely on increasingly longer observation windows. However, the benefit of increasing the window size is often simply attributed to capturing long-range dependencies, and broader discussion on how global forecasting models leverage input observations has been limited. In this paper, we show that forecasting groups of time series involves two objectives: (i) generative process...
-
49
A Closer Look at In-Distribution vs. Out-of-Distribution Accuracy for Open-Set Test-time Adaptation
Zefeng Li, Evan Shelhamer
cs.LG · cs.CV
Open-set test-time adaptation (TTA) updates models on new data in the presence of input shifts and unknown output classes. While recent methods have made progress on improving in-distribution (InD) accuracy for known classes, their ability to accurately detect out-of-distribution (OOD) unknown classes remains underexplored. We benchmark robust and open-set TTA methods (SAR, OSTTA, UniEnt, and SoTTA) on the standard corruption benchmarks of...
-
50
Flow-Transformed Implicit Processes for Function-Space Variational Inference
Luis A. Ortega, Andrés R. Masegosa, Thomas D. Nielsen
cs.LG · stat.ML
Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performing posterior inference with such priors is challenging because their induced function-space distributions are typically not available in closed form. One practical strategy is to approximate the prior using a finite collection of sampled functions, and then represent...
-
51
Randomized Least Squares Value Iteration itself is Joint Differentially Private
Haiyang Lu, Pratik Gajane, Shaojie Bai, Mohammad Sadegh Talebi
cs.LG
As reinforcement learning (RL) increasingly applies to sensitive domains, such as health care and recommendation systems, privacy-preserving techniques have become essential to protect users' sensitive information. We investigate privacy-preserving RL under an episodic setting, focusing on algorithms based on randomized exploration, such as Randomized Least Squares Value Iteration (RLSVI). The overall goal is to study how randomized...
-
52
HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression
Minghui Zheng, Hongxu Chen, Huimin Ren, Hongsheng Xin, Xiaoyang Qu, Ze Wang, Shuling Yang, Ziyu Peng, Kaike Zhang,...
cs.LG · cs.CL
Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial inference overhead. Existing CoT compression methods struggle with inflexible manual length budgets, computationally expensive multi-stage training pipelines, and fragile scalability restricted to small models. We propose HMPO (Hybrid Median-length Policy Optimization), a cost-effective, single-stage...
-
53
Private and Stable Test-Time Adaptation with Differential Privacy
Zefeng Li, Qiaoyue Tang, Mathias Lecuyer, Evan Shelhamer
cs.LG · cs.CV
Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference. However, these updates raise the issue of privacy w.r.t. the testing data, because the model parameters now depend on all past inputs. To control this privacy risk, we cast multiple popular TTA methods (Tent, EATA, SAR, DeYO, and COME) into differential privacy (DP) forms that apply per-sample gradient clipping and...
-
54
Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation
Woojun Jung, Susik Yoon
cs.LG
Real-world domains often contain heterogeneous tables whose headers vary while their underlying attribute semantics are shared, making it difficult to induce domain-specialized semantics from table-local evidence alone. Existing encoders model parts of this problem, but often underuse column-level value distributions and apply uniform objectives across attributes with different semantic roles. We propose NAVI, a segment-centric pretraining...
-
55
Beyond the Simplex: Balanced Prototype Geometry for Scorer-Agnostic Open-Set Recognition
Mayank Sharma, Rohit Kumar Mourya
cs.LG · cs.CV
Open-set recognition (OSR) requires a classifier to reject inputs from unseen classes which is essential in safety-critical settings such as medical imaging. Simplex based methods, which fix class prototypes at the vertices of a regular simplex and then reject via a distance-ratio score, perform well empirically but lack theoretical justification, and existing analysis applies only when the embedding dimension d is at least C-1, which is the...
-
56
G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs
Yuhan Wang, Yibo Ding, Yutong Ye, Mufan Zhao, Wenbo Zhang, Ruijie Wang, Jianxin Li
cs.LG
LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning. While effective on individual downstream tasks, we observe severe catastrophic forgetting when such models are sequentially fine-tuned on streaming tasks. Although parameter-efficient fine-tuning alleviates forgetting to some extent, it remains...
-
57
Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
Manu Srinath Halvagal, Sebastian Lee, SueYeon Chung
cs.LG
Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience. Modern deep RL has shown remarkable success across many domains, further strengthening this connection. The ability to learn abstract representations of high-dimensional state spaces underlies much of this success. However, theoretical understanding of these learned representations remains limited, hindering direct comparisons between...
-
58
Continual Learning as a Multiphase Moving-Boundary Problem
Snigdha Chandan Khilar
cs.LG · math-ph
Continual learning struggles to balance retaining past knowledge with absorbing new tasks. Stefan-CL elegantly resolves this stability-plasticity dilemma through the physics of melting. It frames consolidated knowledge as a protected "solid" and unused capacity as an adaptable "liquid." As the network learns, this boundary expands, governed by a "latent heat" tuning dial. By mathematically freezing the learned interior, Stefan-CL cuts...
-
59
A Theoretical Framework for Self-Play Theorem Proving Algorithms
Thomas Chen, Zhiyuan Li
cs.LG
Self-play, a type of training algorithm that enables a model to self-improve, has recently shown promising empirical results in the context of formal theorem proving using Large Language Models (LLMs). (Dong & Ma, 2025) instantiate self-play with two cooperating agents: a prover, which proves theorems, and a conjecturer, which generates new theorems as a curriculum to the prover. In this paper, we provide a theoretical framework for...
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.