cs.LG · 2026-07-03 · No. 42
Machine Learning, 2026-07-03.
55 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
55 entries-
01
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie, Stuart Shieber, Yuntian Deng
cs.LG · cs.AI · cs.CL
Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large language model APIs at the cost of locality, reproducibility, and price. We propose fuzzy-function programming: compiling such a function from a natural-language specification into a compact, locally-executable neural artifact....
-
02
DemoPSD: Disagreement-Modulated Policy Self-Distillation
Yunhe Li, Hao Shi, Wenhao Liu, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Shuang Qiu, Linqi Song
cs.LG · cs.AI
On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns, suppress exploration, and hurt cross-domain...
-
03
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials
Gil Harari, Yoel Zimmermann, Ola Tangen Kulseng, Laura Zichi, Chuin Wei Tan, Marc L. Descoteaux, Boris Kozinsky
cs.LG · cs.AI · physics.chem-ph · physics.comp-ph
Machine learning interatomic potentials (MLIPs) have become a hallmark of AI for scientific simulation. While efforts on new architectures and datasets have led to increasingly accurate and general models, the choice of optimizer for training has largely remained unexplored, defaulting to Adam and its variants in the community. Here, we implement and systematically compare a class of recently proposed matrix-structured optimizers, including...
-
04
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
Zhuowei Chen, Xiang Lorraine Li
cs.LG · cs.AI
Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain. Recent annotation-free self-evolution methods address this by using the model's own outputs as supervision signals, constructing a teacher via additional context and aggregating predictions across multiple rollouts through...
-
05
Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data
Xuanyu Chen, Nan Yang, Shuai Wang, Dong Yuan
cs.LG
Recent research has introduced distributed self-supervised learning (D-SSL) approaches to leverage vast amounts of unlabeled decentralized data. However, D-SSL faces the critical challenge of data heterogeneity, and there is limited theoretical understanding of how different D-SSL frameworks respond to this challenge. To fill this gap, we present a rigorous theoretical analysis of the robustness of D-SSL frameworks under non-IID...
-
06
Extreme Adaptive Transformer for Time Series Forecasting
Sanjeev Shrestha, Hui Liu, Yifan Zhang
cs.LG
Time series forecasting remains challenging when the underlying data contain rare but critical extreme events. This issue is particularly important in hydrologic forecasting, where streamflow distributions are often highly skewed and extreme peaks can have substantial impacts on flood monitoring, water resource management, and early warning systems. Although Transformer-based forecasting models have achieved strong performance by modeling...
-
07
QFedAgent: Quantum-Enhanced Personalized Federated Learning for Multi-Agent Activity Recognition
Quoc Bao Phan, Tuy Tan Nguyen
cs.LG · cs.AI
Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data, making it suitable for privacy-sensitive robotic sensing applications. However, multi-agent systems generate heterogeneous and non-independent and identically distributed (non-IID) multimodal sensor streams that degrade conventional FL algorithms, while classical fusion modules introduce substantial parameter overhead and...
-
08
Neuron-Aware Active Few-Shot Learning for LLMs
Zhuowei Chen, Liwei Chen, Christian Schunn, Raquel Coelho, Xiang Lorraine Li
cs.LG · cs.AI
Active Few-Shot Learning (AFSL) adapts LLMs to specialized domains by identifying the most valuable unlabeled samples for annotation and use as few-shot demonstrations, effectively reducing human annotation costs while promoting high performance. However, existing methods typically rely on output-level signals for sample identification, such as predictive entropy or semantic similarities with test-time data based on external embeddings, which...
-
09
DecompRL: Solving Harder Problems by Learning Modular Code Generation
Juliette Decugis, Fabian Gloeckle, Francis Bach, Taco Cohen, Gabriel Synnaeve
cs.LG
How can Large Language Models (LLMs) solve problems they currently cannot? Repeated sampling scales test-time compute but GPU cost grows linearly with attempts, while reinforcement learning (RL) with verifiable rewards improves single-attempt accuracy at the expense of sample diversity. Both strategies ultimately fail when the base policy has near-zero probability of producing a correct solution: no amount of sampling or gradient signal can...
-
10
Self-Gating Attention for Efficient Time Series Forecasting
Dezheng Wang, Tong Chen, Wei Yuan, Congyan Chen, Shihua Li, Hongzhi Yin
cs.LG · cs.AI
Transformer architectures have shown strong potential in time series forecasting, where multi-head self-attention is widely used to capture temporal dependencies across historical timestamps. However, standard self-attention has quadratic time and memory complexity with respect to the look-back length. This cost may limit its use in resource-constrained or high-throughput forecasting systems, where fast and memory-efficient inference is...
-
11
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
Juan Agustín Duque, Sergio García Heredia, Vinicius Hernandes, Eliška Greplová, Thomas Spriggs, Aaron Courville, Anna Dawid
cs.LG · cond-mat.dis-nn · quant-ph
Neural quantum states (NQS) provide a flexible and scalable framework for approximating quantum many-body wavefunctions. Among NQS parameterizations, autoregressive models are especially attractive because they enable exact, independent sampling from the Born distribution, avoiding the autocorrelation and mixing issues of Markov chain methods. Yet their optimization remains comparatively underexplored: Adam is a scalable method but ignores...
-
12
Optimizing Visual Generative Models via Distribution-wise Rewards
Ruihang Li, Mengde Xu, Shuyang Gu, Leigang Qu, Fuli Feng, Han Hu, Wenjie Wang
cs.LG · cs.CV
Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies. To address these limitations, we present a novel framework that finetunes generative models using distribution-wise rewards, ensuring better alignment with real-world data distributions. Unlike rewards that...
-
13
Generalization in offline RL: The structure is more important than the amount of pessimism
Max Weltevrede, Matthijs T. J. Spaan, Wendelin Böhmer
cs.LG · cs.AI
While pessimism counteracts overestimation bias in offline reinforcement learning (RL), being overly conservative has been associated with hindering certain forms of generalization. However, in this paper we demonstrate that being overly pessimistic does not inherently prevent optimal generalization in contextual MDPs (CMDPs). Instead, we argue successful generalization depends not on the amount of pessimism, but whether the pessimistic...
-
14
HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures
Ziyun Qiao, Yue Min, Ruining Chen, Yujun Li
cs.LG · cs.AI · cs.CL
Most data-mixing methods assume the corpus has already been partitioned into groups, and the choice of those groups determines what a mixer can express. Existing labels, including provenance, topic or format taxonomies, and flat embedding clusters, commit to one semantic axis at one granularity; changing the resolution rebuilds the labels. We argue the bottleneck is the label system, not the mixer, and provide a hierarchical one. HERMES is a...
-
15
Self-explainable Operator Learning for Discovering Spatial Patterns in Functional Data
Mojgan Alishiri, Amirhossein Arzani
cs.LG · physics.flu-dyn
Operator learning has emerged as a powerful tool for modeling complex physical systems in functional spaces. However, their neural network-based architectures make them opaque models, obscuring the reasoning behind their predictions. In this work, we introduce a self-explainable operator learning framework that overcomes this challenge by reformulating operator learning as a linear combination of generalized functional linear models expressed...
-
16
Online Resource Allocation with Continuous Random Consumption: Regret under Degeneracy
Jiawei Zhang
cs.LG
We study online resource allocation when both rewards and consumption sizes may be continuously distributed. Requests arrive sequentially and must be accepted or rejected irrevocably under fixed resource capacities. Each request belongs to one of finitely many observable types; conditional on an observable request type, both the reward and the scalar size are random, and the realized size scales a fixed type-specific resource-consumption...
-
17
An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks
Joseph Webb, Sadok Jerad, Coralia Cartis
cs.LG · math.NA · math.OC · physics.comp-ph
Physics-informed neural networks (PINNs) have emerged as a promising route to solve partial differential equations, yet they have struggled to reach the precision of classical solvers. The obstacle is increasingly understood to be one of optimisation, owing to the severely ill-conditioned loss landscape. We present $\textbf{DSGNAR}$: Doubly-Sketched Gauss-Newton with Adaptive Ratio, a scalable second-order optimisation framework that...
-
18
Privacy-Preserving and Verifiable Approximate Distributed Coded Computing
Xavier Martínez-Luaña, Alba Gude-Santos, Manuel Fernández-Veiga, Rebeca P. Díaz-Redondo
cs.LG · cs.CR
Distributed machine learning enables collaborative model training without centralizing data, but it also exposes learning processes to privacy leakage and malicious manipulation. Existing defenses typically address these threats in isolation and are often tailored to specific learning paradigms or model architectures, limiting their applicability in realistic deployments. In particular, federated learning and decentralized learning exhibit...
-
19
Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimation
Jijie Zhang, Zhe Ren, Quan Zhang, Dandan Guo
cs.LG · cs.CL
Large language models (LLMs) exhibit remarkable reasoning capabilities, but their task-specific fine-tuning is notoriously plagued by overconfidence, severely hindering trustworthy deployment. We propose Data-Adaptive Lower-Rank Adaptation (DALorRA), a simple and effective variational Bayesian sparse framework that shifts the paradigm of uncertainty quantification from the dense parameter space to the lightweight rank level of low-rank...
-
20
Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space
Di Wu, Huan Liu, Zhixiang Chi, Yuanhao Yu, Konstantinos N. Plataniotis, Yang Wang
cs.LG · cs.AI
The rapid advancements in using neural networks as implicit data representations have attracted significant interest in developing machine learning methods that analyze and process the weight spaces of other neural networks. However, efficiently handling these highdimensional weight spaces remains challenging. Existing methods often overlook the sequential nature of layer-by-layer processing in neural network inference. In this work, we...
-
21
Predicting Early Stages Of Alzheimer's Disease And Identifying Key Biomarkers Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies
Debopriya Ghosh
cs.LG · cs.AI · cs.CV · cs.NE · eess.IV
Alzheimers disease (AD) is a brain disorder that develops slowly and mainly affects memory, thinking, language, and daily activities. It is one of the most common causes of dementia and creates many difficulties for patients as well as their families. In the early stage, the symptoms are often mild and may look like normal ageing. For this reason, many people are diagnosed late, when the disease has already progressed. At present, there is no...
-
22
Probing Chemical Language Models: Effects of Pre-training and Fine-tuning
Anna Karnysheva, Dietrich Klakow, Ji-Ung Lee
cs.LG
Chemical language models (CLMs) are trained with linearized representations such as SMILES, yet it remains unclear which chemically meaningful substructures they encode. To foster a better understanding of CLMs, we conduct a systematic study and probe for 78 molecular substructures across eight pre-trained and six randomly initialized models. We furthermore study how fine-tuning on chemical downstream tasks affects the learned representations...
-
23
ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning
Yilie Huang, Wenpin Tang, Xun Yu Zhou
cs.LG · cs.AI · eess.SY · math.OC
We study timestep allocation for score-based diffusion sampling, where a learned reverse-time dynamics is discretized on a finite grid. Uniform and hand-crafted schedules are standard choices, but they rely on fixed prescriptions and can therefore be suboptimal. To address this limitation, we propose Adaptive Reparameterized Time (ART), a continuous-time control formulation that learns a time change by treating the speed of the sampling clock...
-
24
Predictive Conformal Slip Monitoring: An Empirical Evaluation of Rolling Split Conformal Prediction for Pre-Incident Traction Loss Detection
Varshith Roy Kotla
cs.LG · stat.AP
Conventional traction control architectures intervene only after the adhesion limit of a tire has already been breached. This paper investigates whether Rolling Split Conformal Prediction , monitoring the volatility of non-conformity residuals from a per-driver Random Forest model of expected slip behavior , can serve as a statistically grounded pre-incident warning signal, ahead of gross traction loss. Unlike an earlier internal draft of...
-
25
Ask the Right Comparison:Bias-Aware Bayesian Active Top-$k$ Ranking with LLM Judges
Jian Xu, Delu Zeng, John Paisley, Qibin Zhao
cs.LG
Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers. Yet LLM judges are both noisy and systematically biased: they favor verbose or well-formatted answers and exhibit position effects, so simply aggregating their votes recovers a ranking of presentation, not of true quality. We study the practical goal of identifying the...
-
26
Fourier Neural Operators for Rayleigh-Bénard Convection
Chelsea Maria John, Thibaut Lunet, Sebastian Götschel, Andreas Herten, Stefan Kesselheim, Daniel Ruprecht
cs.LG · physics.flu-dyn
We propose an improved Fourier Neural Operator (FNO) for modeling two-dimensional Rayleigh-Bénard convection by predicting time increments instead of full solutions, achieving higher accuracy than a standard FNO baseline. The resulting model is compact (314k parameters, 1.26 MB) and fast (7 ms inference), while maintaining similar accuracy as demonstrated in previous benchmarks. We show that although FNOs generalize to finer meshes, accuracy...
-
27
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan
cs.LG · cs.AI · cs.CR
Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominately rely on fine-tuning to build classifiers, which often suffer from low generalization and high inference latency. We present kNNGuard, a training-free guardrail that utilizes the activation space of an off-the-shelf LLM. Given a small bank of 50 safe and unsafe prompts,...
-
28
SA-HGNN: Sample-Adaptive Hyperbolic Graph Neural Network for EEG-Based Depression Recognition
Yang Li, Pan Hu, Yan Zhang, Wenfan Yang, Tao Wu, Lianbo Guo
cs.LG · cs.AI
Graph Neural Networks (GNNs) have been widely used to capture spatial functional connectivity patterns to improve electroencephalography (EEG)-based depression recognition performance. However, the functional connectivity of brain networks in patients with depression exhibits an inherent hierarchical structure, making it difficult to capture accurate connection patterns. To address these issues, this paper proposes a novel model named...
-
29
Beyond the Performance Illusion: Structure-Aware Stratified Partitioning and Curriculum Distributionally Robust Optimization for Spatially Correlated Domains
Prathamesh Patil, Arpit Jain, Aswanth Krishnan
cs.LG · cs.AI · cs.CV
Performance evaluation in AI systems commonly assumes that random dataset splits produce independent and identically distributed (i.i.d.) subsets. We show that this assumption often breaks down in spatiotemporally correlated domains such as aerial surveillance, precision agriculture, and medical imaging, leading to two systematic failures: data leakage, where correlated samples span training and validation splits and inflate performance...
-
30
A Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems
Yuval Ran-Milo, Angelos Assos, Elad Hazan
cs.LG · eess.SY
Motivated by the challenge of stabilizing a general unknown linear dynamical system (LDS) from observations, we study the natural prerequisite of online prediction. Our goal is to achieve sublinear regret with a memory footprint that adapts to the intrinsic complexity of the dynamics rather than the full hidden -- state dimension. We focus on the practically central regime of systems with low instability complexity -- eigenvalues outside the...
-
31
Fast and Accurate Anomaly Detection in Time Series
Emanuele Mele, Massimo Cafaro, Angelo Coluccia, Italo Epicoco
cs.LG
Anomaly detection is a critical and evolving field in Machine Learning, with applications targeting different domains such as cybersecurity, finance, healthcare, manufacturing and IoT (Internet of Things) systems. Traditionally, anomaly detection algorithms have been designed using both supervised and unsupervised learning paradigms. The fundamental challenge in real-world anomaly detection scenarios is related to the inherent class imbalance...
-
32
Liquid Latent State Dynamics for Interpretable Turbofan Degradation Modeling
Weizhi Nie, Weijie Wang, Yuting Su
cs.LG · cs.CV
Multivariate time-series models for prognostics are often evaluated by point prediction accuracy, yet their internal states rarely expose a coherent degradation process. We study liquid neural networks as latent dynamics models for aircraft engine health monitoring on the C-MAPSS benchmark. The proposed model encodes a history window into a latent state, evolves that state with a liquid transition model, and decodes future sensor...
-
33
Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency
Tasnim Shahriar
cs.LG · cs.AI · cs.CV
Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation. This study compares nine lightweight CNN model packages across CIFAR-10, CIFAR-100, and Tiny ImageNet under a shared downstream protocol. We report top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 storage, GMACs, batch-size-1 latency on an NVIDIA L4 and...
-
34
Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics
Benedikt Kaas, Manuel Treutlein, Hannes Benedikt Gerber, Oliver Neumann, Cheewan Phatthanakhuha, Oliver Resch, Ralf...
cs.LG
Low-voltage load forecasting is an important component in current and future energy systems with a high degree of electrification and decentralized generation. However, current forecasting methods require significant manual effort, often lack uncertainty estimation and proper peak prediction, and they are often not adequately evaluated in terms of grid requirements. In the present study, we provide an extensive evaluation of short-term net...
-
35
A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods
Koki Konishi, Masataka Ushiku, Yuta Saito
cs.LG
A/B testing is the gold standard for selecting the better algorithm in online services. While offline evaluation has attracted attention as a safer alternative due to the high experimental costs and the potential risk of degrading user experience and revenue in A/B testing, it is widely recognized that the estimation accuracy of offline evaluation is substantially lower. As a result, final selection decisions are typically made through A/B...
-
36
Hybrid quantum-classical neural network for sentiment analysis
Giacomo Cappiello, Filippo Caruso, Xing Liang, Dimitrios Makris
cs.LG · quant-ph
Quantum machine learning has recently emerged as a promising paradigm that leverages the expressive power of quantum circuits to address complex learning tasks. In this work, we investigate the applicability of hybrid quantum-classical neural networks to sentiment analysis, a central problem in natural language processing. We focus on a dataset of tweets related to COVID-19, where the textual content is vectorized using TF-IDF and fed into...
-
37
Conditional Co-Ablation: Recovering Self-Repair Backups in Transformer Circuits
Zhiren Gong, Zihao Zeng, Chau Yuen, Wei Yang Bryan Lim
cs.LG · cs.AI
Mechanistic interpretability often relies on component-level interventions to discover how a model produces a behavior. This guides attribution, capability knockout, and model pruning downstream to operate by scoring each unit by the effect of ablation in isolation. Such first-order scoring is natural when component importance is additive, but becomes misleading when a transformer self-repairs: after a primary component is removed, a dormant...
-
38
Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
Yisong Fu, Zezhi Shao, Chengqing Yu, Yujie Li, Yongjun Xu, Xueqi Cheng, Fei Wang
cs.LG
We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. Unlike prior studies that primarily focus on zero-shot forecasting but require task-specific tuning for other tasks, Zeus bridges this gap by addressing two fundamental challenges in multi-task generalization. First, to reconcile point-level granularity with...
-
39
Population-Based Multi-Objective Training of Discriminators for Semi-Supervised GANs
Francisco Sedeño, Francisco Chicano, Jamal Toutouh
cs.LG · cs.AI · cs.CV
Semi-supervised generative adversarial networks (SSL-GANs) can exploit large unlabeled datasets while retaining a classifier in the discriminator, but their training is often unstable. This paper proposes a population-based evolutionary training strategy in which discriminator learning is formulated as a multi-objective optimization problem. Instead of aggregating the supervised and unsupervised components of the SSL objective into a single...
-
40
SABER: A Semantic-Aligned Brain Network Analysis Framework via Multi-scale Hypergraphs
Yidan Xu, Xiangmin Han, Rundong Xue, Huihui Ye
cs.LG · cs.AI · cs.MM
Effective brain disease diagnosis requires the synergy of brain connectivity patterns and high-level semantic knowledge. Existing methods, however, largely treat semantics from large language models (LLMs) as auxiliary features or supervision, limiting their direct role in decision-making and constraining classification stability and robustness. To overcome this, we propose a semantic-aligned brain network framework that actively integrates...
-
41
Rank-Then-Act: Reward-Free Control from Frame-Order Progress
Yuriy Maksyuta, George Bredis, Ruslan Rakhimov, Daniil Gavrilov
cs.LG · cs.AI
We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards. RTA trains a Vision-Language Model (VLM) offline as a progress-based ordinal scorer, using a Group Relative Policy Optimization (GRPO) objective over shuffled frame sequences, which forces the model to recover temporal ordering from visual semantics rather than trivial time cues. Importantly, instead of...
-
42
Regularized Variational and Spectral Log-Density-Ratio Estimation in the Gaussian Location Model
Francis Bach
cs.LG · math.OC · math.ST · stat.ML
We study ridge-regularized log-density-ratio estimation in the Gaussian location model with a common covariance matrix. By affine invariance, the model is written as q $\sim$ N(0, I), p $\sim$ N($Δ$, I), with linear features, where $Δ$ is a mean vector. The variational estimator is the empirical Kullback-Leibler (KL) log-normalized fit with a squared L2-penalty on its nonconstant coefficient, and the spectral estimator recently introduced in...
-
43
Learning the Supports for Categorical Critic in Reinforcement Learning
Jen-Yen Chang, Takayuki Osa, Tatsuya Harada
cs.LG
Value functions are an essential component in actor-critic based deep reinforcement learning (RL). Conventionally, these functions are trained as a regression task by minimising the mean squared error (MSE) relative to bootstrapped target values. Meanwhile, in distributional RL, a distribution of returns is modelled based on the distributional Bellman operator. This work investigates the Gaussian Histogram Loss (HL-Gauss), a recent approach...
-
44
Decomposer: Learning to Decompile Symbolic Music to Programs
Yewon Kim, Apurva Gandhi, David Chung, Graham Neubig, Chris Donahue
cs.LG · cs.AI · cs.SD
Musical performance involves executing a set of high-level musical instructions, yet recovering those instructions from the performance is a challenging inverse problem. We present Decomposer, a post-training framework for symbolic music decompilation: the task of recovering executable, editable music programs from symbolic music. We instantiate the task as MIDI-to-Strudel decompilation, where the model takes symbolic MIDI as input and...
-
45
Adaptive Group-Based Counterfactual Explanations for Time-Series Rehabilitation Data
Emmanuel C. Chukwu, Rianne M. Schouten, Monique Tabak, Mykola Pechenizkiy
cs.LG
Counterfactual explanations (CEs) for multivariate time-series classifiers are often difficult to interpret in domains where experts reason in terms of semantic feature groups rather than individual channels. In rehabilitation movement analysis with multi-sensor inertial measurement units (IMUs), clinicians interpret motion through muscle-group and joint-segment abstractions; yet, most existing counterfactual methods operate at the channel...
-
46
Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling
Dazhi Fu, Jiuding Yang, Yiwen Guo, Jicong Fan
cs.LG
Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator. As a result, they may overlook important dimensions of human preference, a failure mode we term dimensional blind spots....
-
47
Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking
Nikil Roashan Selvam, Jay Baxter, Sophie Hilgard, Brad Miller, Keith Coleman, Ellen Vitercik, Sanmi Koyejo
cs.LG
Crowdsourced fact-checking systems have been adopted by major social media companies such as X, Meta, TikTok and Google with the aim of combating misleading information at scale without relying on centralized editorial control. These systems have been developed around a common underlying concept: a bridging mechanism that identifies notes flagging misleading information when they receive support from people with different perspectives rather...
-
48
Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis
Jiatong Li, Weida Wang, Changmeng Zheng, Shufei Zhang, Yatao Bian, Xiao-yong Wei, Qing Li
cs.LG · cs.CL
Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains between their probabilistic nature over discrete sequential tokens and the rigid topological constraints of chemical space. This raises the question of whether molecular LLMs can generalize beyond the local neighborhoods induced by their sequence-based representations. To systematically investigate this question, we introduce a Molecular...
-
49
Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability
Rodrigo Mendoza-Smith
cs.LG · cs.AI · cs.IT
Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcomplete dictionary $\mathbf{W}\in\mathbb{R}^{m\times n}$ with $m<n$, and inferring a sparse code $\mathbf{x}\in\mathbb{R}^n$ from $\mathbf{h}\approx\mathbf{W}\mathbf{x}$. This inference problem closely resembles the canonical setup of compressed sensing, but dense decoders requires $O(mn)$ learned...
-
50
Single-Channel EEG-Based Cognitive Load Assessment in Online Learning: A Hybrid Deep Learning Approach
Rowan Hussein, Mohamed Ouf
cs.LG · cs.AI
Monitoring cognitive load during online learning could help instructors identify content that learners find difficult, but remote settings remove the visual cues that support this judgement in a classroom. We study whether a single-channel, consumer-grade EEG device (the NeuroSky MindWave Mobile 2) can distinguish easy from difficult educational-video content, using the publicly available dataset of Wang et al. [24] (ten learners, one...
-
51
EPnG: Adaptive Expert Prune-and-Grow for Parameter-Efficient MoE Fine-tuning
Ahin Lee, Sehyun Yun, Taesik Gong
cs.LG · cs.AI
Mixture-of-Experts (MoE) models scale efficiently but remain costly to adapt due to redundant experts and uniform parameter allocation. Existing parameter-efficient fine-tuning (PEFT) methods such as LoRA ignore MoE routing dynamics, leading to suboptimal resource use. We propose EPnG, an adaptive prune-and-grow framework that reallocates LoRA capacity based on expert importance derived from router gate probabilities. EPnG prunes...
-
52
EHHN: An Event-driven Heterogeneous Hypergraph Network for Object-Centric Next Activity Prediction
Jiaxing Wang, Kaitao Chen, Zhubin Han, Chenyu Hou, Bin Cao, Jing Fan, Ji Zhang
cs.LG
Next activity prediction helps service-oriented processes anticipate upcoming steps before delays, exceptions, or service-level risks occur. Most existing methods assume classical single-case event logs, whereas real service processes often involve events shared by multiple typed business objects. Object-centric event logs (OCELs) capture such interactions, but current predictors remain limited. Flattening-based approaches lose cross-object...
-
53
Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding
Marianne Arriola, Volodymyr Kuleshov
cs.LG
Discrete diffusion models have steadily improved in quality relative to autoregressive (AR) models. However, these models are normally constrained to fixed-length generation and do not support key-value (KV) caching. Block diffusion partially bridges diffusion and AR by generating token blocks left-to-right, but its fixed-size sequential blocks limit decoding flexibility and parallelism. Here, we present a new class of language models, set...
-
54
Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Meng Wang, Haohan Zhao, Wenzhuo Liu, Lu Yang, Geng Liu, Haiyang Guo, Guo-Sen Xie, Gaofeng Meng, Hongbin Liu, Fei Zhu
cs.LG · cs.CL
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgetting, with on-policy self-distillation emerging as a particularly attractive approach. In this work, we revisit this optimistic view through self-distillation policy optimization (SDPO). Our experiments show that SDPO can accelerate in-domain specialization when...
-
55
Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning
He Huang, Lu Shen, Yunfeng Huang, Li Qi
cs.LG · stat.ML
Many representation learning problems involve directed relations, such as lexical entailment, sentence entailment, ontology hierarchy, and citation links. Standard Euclidean, cosine, and Mahalanobis heads are symmetric, while generic neural scorers can model directionality but provide limited geometric structure. This paper proposes a role-aware neural convex divergence head for asymmetric representation learning. The head applies source- and...
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.