cs.LG · 2026-08-05 · No. 75
Machine Learning, 2026-08-05.
43 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
43 entries-
01
Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
Mohsen Hariri, Weicong Chen, Nahal Shahini, Vikash Singh, Kai Ye, Amirhossein Samandar, Debargha Ganguly, Sreehari...
cs.LG · cs.AI
Large language models can solve substantially harder reasoning problems with more inference-time compute. The term "test-time scaling," however, now covers diverse inference algorithms that extend deliberation along a single trajectory, sample completed candidates and aggregate them through voting or verification, or search over unfinished partial states. These algorithms differ in their statistical structure, compute accounting, and failure...
-
02
Assessment of Conditional Diffusion Model for Synthetic Histopathology Image Generation
Seyed Kahaki, Shijie Li, Weijie Chen, Nicholas Petrick
cs.LG
Synthetic histopathology image generation has emerged as an approach that may address data scarcity in computational pathology, yet current evaluation methodologies may not fully assess synthetic data quality for medical applications. This work investigates and addresses limitations in existing evaluation metrics, investigating an approach for assessing synthetic histopathology image quality through domain-specific metrics and downstream task...
-
03
Muon Meets Mamba: Spectral Optimization for State Space Models
Arslan Battalov, Karim Kramin, Alexander Markotenko, Sofia Sinitsina
cs.LG
Muon is a recent optimizer that orthogonalizes the update to each weight matrix with a Newton-Schulz iteration, which performs steepest descent under the spectral norm. Almost all the evidence for it comes from Transformer models, and its behavior on state-space models is largely unreported. We compare Muon with AdamW on Mamba-2 130M under a controlled protocol that varies only which weight groups are trained with Muon. The benefit is...
-
04
Latent Reward Registers for Diffusion Preference Alignment
Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun
cs.LG · cs.CV
Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process. We propose Latent Reward Registers, a mechanism that estimates terminal preference directly from intermediate noisy latents by prepending learnable, position-free register tokens to the input sequence of a frozen...
-
05
A Physics-Flavored Transformer Network for Parametrizing Contraction Dynamics of Engineered Skeletal Muscle Tissues
Mattias Luber, Timo Betz
cs.LG
Engineered Skeletal Muscle Tissues (ESMs) have become a key structure for biomedical disease modeling and pharmacological screening, yet their functional characterization often relies on simplistic metrics like peak force, discarding critical kinetic information. This is partially due to the high level of mathematical complexity which mechanistic models introduce to capture these dynamics. Hence, exactly the complexity prevents scalable...
-
06
PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection
Mateusz Smendowski, Kamil Faber, Piotr Nawrocki, Nathalie Japkowicz, Roberto Corizzo
cs.LG · cs.AI · cs.CV
Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices, especially in multivariate settings. While transforming time series into images has shown success in forecasting and classification, it remains unclear how multivariate, high-dimensional series should be mapped to multi-channel images and whether vision backbones...
-
07
Trajectory inference via Acceleration Matching
Bartolo Dazzini, Giovanni Conforti, Alain Durmus, Aram-Alexandre Pooladian
cs.LG · math.OC · stat.ML
Trajectory inference is a fundamental problem in many scientific domains: given a collection of unpaired snapshots of observations at discrete time points, the goal is to generate smooth trajectories that best resemble and interpolate the data. Existing algorithms exhibit computational challenges: they either rely on preprocessing subroutines to enforce smoothness or on simulation-based training objectives, both of which can be expensive. In...
-
08
Sparse Weight Decomposition for Efficient Circuit Extraction
Chuanhao Yan, Xuhan Huang, Yawen Duan, Zhenfei Yin, Hang Zhao, Bryan Dai, Jie Fu
cs.LG · cs.CL
Dense pretrained transformers do not naturally expose interpretable units for circuit extraction. Existing approaches obtain such units by learning auxiliary sparse representations or training sparse models, incurring substantial additional computation while potentially introducing a fidelity gap between the representation being analyzed and the original pretrained model. We propose Sparse Weight Decomposition (SWD), which reparameterizes...
-
09
Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse
Taekyung Heo, Rasoul Shafipour, Ritchie Zhao, Maximilian Golub, Mohammad Mahdi Kamani, Ritika Borkar, Makesh Tarun...
cs.LG
Production deployments often swap between different-sized models in a family for cost-quality cascading, mid-conversation switching, and routing, and each swap forces the receiver to repay the prefill from scratch. We propose cross-model KV cache transfer, where the receiver reuses the source's KV cache, skipping prefill. We find that cross-model KV has substantial linear structure across matched-KV pairs, where source and target share KV...
-
10
Omega-S: A Functional Resilience Index for LLM Fine-Tuning
Alberto Acedo
cs.LG · cs.NE · q-bio.MN
Fine-tuning a large language model on new data degrades what it previously learned. We present Omega-S, a drop-in penalty computed from the weight matrix alone: it needs no previous-task data, no Fisher matrix and no stored copy of the old weights. It is three lines in an existing training loop and adds under 4% to the cost of a step. Retention. On Llama-3-8B with LoRA, fine-tuned from code to prose and measured by HumanEval over ten seeds,...
-
11
Operationally Feasible Synthetic Power-Grid Scenarios via Learning the AC-Operable Joint Distribution
Chenhan Xiao, Xinyu He, Haoran Li, Hanghang Tong, Yang Weng
cs.LG · eess.SY
Synthetic power-grid scenarios are essential for planning, resilience assessment, contingency analysis, and data-driven power-system applications. Recent synthetic grid generation methods have improved structural realism and operational feasibility by incorporating engineering knowledge through post-generation validation, optimization, or physics-aware generation. However, generated scenarios may still exhibit low AC feasibility and...
-
12
Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning
Pyrros Koussios, Chenhao Li, Xin Chen, Andreas Krause
cs.LG · cs.AI
Designing effective reward functions remains a major bottleneck in Reinforcement Learning (RL). Recent work uses large foundation Vision-Language Models (VLMs) as reward models, computing text-observation similarity to bypass manual reward engineering. Although promising, these rewards are often noisy and unreliable, limiting their direct utility during deployment. We present Structure-Aware Fine-Tuning (SAFT), a simple, self-supervised...
-
13
GENESIS: Towards Explainable Causal Discovery
Abhinav Thorat, Ravi Kumar Kolla, Vishak K Bhat, Harsh Vardhan Singh Chauhan, Niranjan Pedanekar
cs.LG · cs.AI
Causal Discovery (CD) from observational data faces two fundamental challenges. First, purely statistical methods often lack the power to resolve structural ambiguities in low-sample regimes. Second, although LLM-assisted hybrid approaches improve structure recovery through semantic reasoning, the influence of that reasoning on individual edge decisions remains largely opaque. Consequently, existing hybrid methods fail to satisfy a...
-
14
CRS-Triage: Confidence- and Reliability-Aware Selective Triage under Incomplete Clinical Evidence
Guan Qiang, Yushen Chen, Tianlong Liu, David Rotenberg, Ethan H. Kim, Fang Fang
cs.LG
Emergency triage requires reliable decisions within a short time period. However, the available electronic health record (EHR) data, including structured data and clinical text, are often incomplete, unreliable, and inconsistent. This makes machine learning (ML)-based triage prediction more challenging, as existing ML models typically rely on complete and reliable EHR data to accurately predict patients' acuity levels. To address this, we...
-
15
Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language
David Ming Segura, Jeremy Goumaz, Joshua W. Sin, Bojana Ranković, Philippe Schwaller
cs.LG
Transformer models have revolutionized natural language processing (NLP), and text-based molecular representations like SMILES have successfully extended these architectures to chemistry. However, domain-adaptive pre-training often causes models to overfit to chemical syntax, catastrophically forgetting their foundational semantic capabilities. To address this challenge, we introduce CheMatE, a chemistry-oriented embedding model that jointly...
-
16
Quantization Effects on Biomedical LLM Reliability
Anton Rasmussen, Hong Qin
cs.LG
When decoder language models are used as classifiers, predicted class probabilities depend on implementation choices, including the prompt template, verbalizer (label-to-token mapping), and scoring rule, that are rarely treated as experimental variables. We present a controlled evaluation of three Mistral-7B variants (Base, BioMistral, and Instruct) on PubMed RCT sentence classification (n=2000) under FP16, INT8, and INT4 precision using four...
-
17
FedCritic-MIMO: Communication-Efficient Serverless Federated Critic Learning for Massive-MIMO Resource Control in Open and Disaggregated 6G RANs
Amin Farajzadeh, Melike Erol-Kantarci
cs.LG · cs.MA · cs.NI
This paper proposes FedCritic-MIMO, a communication-efficient serverless federated multi-agent reinforcement learning framework for AI-native resource control across independently deployable cell-level controllers in open and disaggregated 6G RANs. Controllers share no trainer, retain local actors and personalized critic components, and exchange only compatible shared critic parameters. FedCritic-MIMO targets reuse-$1$ multi-cell massive-MIMO...
-
18
Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers
Sajjad Khan
cs.LG · cs.DC · cs.LO · cs.SE
A framework that persists execution state so a run can be interrupted, survive a crash, and continue must decide what a resume means for effects that already fired. Five widely deployed agent workflow frameworks answer differently, none exposes a machine-checkable contract, and behavior violates even the fragments they state. The RESUME CONTRACT states six properties over the persistence API (prefix continuation, effect exactly-once, fork...
-
19
UNVaMP: Neural Knowledge Tracing with Variational Regularization of Latent Knowledge Dynamics
Carson J. Cook, Ahmed J. Zerouali, Anthony Schmidt, Reginald Ziedzor, Paul Lin, Luke G. Eglington
cs.LG · cs.CY
We introduce the Unified Neural Variational Measurement of Proficiency (UNVaMP) architecture, a knowledge tracing method that integrates observed student-item interactions with internal memory to produce evolving latent representations of student knowledge. These representations support accurate predictions of future responses while enabling explicit control over the smoothness of estimated learning trajectories. UNVaMP can be configured as...
-
20
Amortized Interventional Forecasting for Multivariate CIR Processes
Andreas Sauter, Sumit Sourabh, Drona Kandhai, Erman Acar
cs.LG · cs.CE
Mean-reverting dynamics are pervasive in finance, and the Cox--Ingersoll--Ross (CIR) process is a standard model for the time series they produce, from short rates to credit default swap (CDS) spreads. Yet CIR models capture only \emph{correlated} co-movement, not \emph{causal} influence between series, so they cannot answer the system's response when one series is externally shocked, which observational conditionals confound with historical...
-
21
To Describe or Construct Statistical Learning Models Using the Category-theoretical Language
Congwei Song
cs.LG
Statistical learning is a fascinating field that has long been the mainstream of machine learning/artificial intelligence. A large number of results have been produced which can be widely applied to real-world problems. It also leads to many research topics and also stimulates new research. This report summarizes some classical statistical learning models and well-known algorithms, especially for amateurs, and provides a category-theoretic...
-
22
Learning and Clustering on Temporal Graphs: Principles, Primitives, and Pooling
Nelson Aloysio Reis de Almeida Passos, Emanuele Carlini, Salvatore Trani
cs.LG · cs.SI
This work focuses on the problem of learning on temporal graphs, with particular emphasis on the task of clustering: obtaining coarse-grained representations by aggregating information from nodes, edges, and temporal dynamics - a task related to pooling in machine learning on graphs, or community detection in network science. Although graph neural networks reach state-of-the-art performance across many downstream graph tasks, their advantage...
-
23
LAEF: A Lead-Agnostic ECG Foundation Model Towards Point-of-Care Diagnostics
Edoardo Coppola, Stefano Fiorini, Pietro Liò, Mattia Savardi, Alberto Signoroni
cs.LG
Point-of-care cardiac devices such as smartwatches and handheld ECG recorders typically capture 1--2 leads, yet existing ECG foundation models are architecturally constrained to fixed 12-lead inputs, degrading or failing under these reduced configurations. We introduce LAEF (Lead-Agnostic ECG Foundation), a 7M-parameter ECG foundation model that can natively process any lead subset without zero-padding or architectural modification. LAEF...
-
24
DiagLoop: A Counterfactual Data Flywheel with Stage-Localized Reinforcement for Diagnostic LLMs
Jian Zhang, Bingyi Wang, Yizhi Liu
cs.LG
Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments. Yet serious cases are scarce, records rarely contain reasoning paths, and data transfer poorly across configurations, complicating local deployment. We present DiagLoop, a counterfactual data flywheel that converts codified physical relations or clinical guidelines, authored once per mechanism family, into training...
-
25
CausalOPD: First-Wrong-Step Supervision for Distilling Causal Chain Reasoning
Jian Zhang, Bingyi Wang, Yizhi Liu
cs.LG
Many critical reasoning tasks, including clinical diagnosis, legal judgment, and industrial fault diagnosis, require step-dependent causal chains in which early errors propagate and correct conclusions can mask invalid reasoning. Although large language models perform well on such tasks, privacy, latency, and controllability motivate distillation into locally deployable models. Standard trajectory imitation does not correct process errors on...
-
26
POEM: Phase-Aware $\mathrm{SO}(2)$ Feature Rotation for Time Series Forecasting Under Periodicity Drift
Jiawen Zhu, Shuhan Liu, Shengxuan Li, Qiming Shi, Di Weng
cs.LG
Deep learning has advanced time series forecasting, but periodicity drift, in which cycle timing and phase vary over time, remains a challenging problem. Existing methods predominantly model these sequences on fixed time grids, suffering from a limited ability to accommodate phase-related variation. To address this limitation, we propose \textbf{POEM}, a phase-aware forecasting framework based on latent feature rotation using the special...
-
27
ConformalShift: Targeted Event Reordering Against Adaptive ECG Monitoring
Arash Vashagh, Yasmin Vashagh
cs.LG
Adaptive conformal prediction can recover clinically important heartbeat classes missed by a point classifier, but delayed feedback makes its decisions sensitive to event order. We introduce ConformalShift, a bounded event-reordering attack that suppresses the ventricular class for rescued events without modifying ECG waveforms, labels, classifier scores, or the event multiset. ConformalShift searches for feasible permutations of authentic...
-
28
A Theory of Conditional Collapse under Low-Rank Weight-Space Ablations: I. The Single-Block Theory and Synthetic Validation
Abdallah Khemais
cs.LG · cs.AI
Activation patching and weight-space ablation both claim a component is causally responsible for a behavior, yet they act on different objects: one forward pass versus the parameters behind every forward pass. We ask when they agree. We study an idealized model where a conditional computation is carried additively through a residual stream, $F(x)=F_0(x)+\sum_iα_i(x)v_i$, read out by a linear functional, and prove three exact results. First,...
-
29
Design-Time Optimization of Deep Neural Networks for Intermittent Learning on Microcontrollers
Jakob Schubert, Maximilian Kasper, Maximilian Linke, Benedict Herzog, Mark Deutel, Axel Plinge, Dominik Seuss,...
cs.LG
We present a method for designing deep neural networks (DNNs) for intermittent, energy-autonomous, on-device learning on microcontroller units (MCUs). In mobile applications where the energy can run out, e.g., when solar-powered, executing artificial intelligence (AI) faces a technical issue as learning can be interrupted at any time. Our approach combines a hardware-aware energy prediction model with multi-objective optimization (MOO),...
-
30
Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving
Xiang Li, Pengcheng Wang, Huazheng Wang, Saurabh Bagchi
cs.LG · cs.AI
Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters. Though powerful, this introduces a critical system dilemma between serving efficiency and task performance: higher-rank adapters generally achieve better downstream task performance, but their GPU VRAM footprint and Host-to-Device PCIe swapping overhead severely constrain scalability. Conversely, ultra-low-rank adapters ($r \le...
-
31
Robust General Utility for Reinforcement Learning
Zixuan Liu, Fangzheng Wu, Brian Summa, Zizhan Zheng
cs.LG
Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measure, thereby enabling a broader range of applications. However, previous work on general utility RL typically assumes the evaluation utility is fixed and correctly specified. In practice, the utility used at deployment can deviate from the training one, creating a robustness gap that prior work...
-
32
FedCARE: A Multi-Objective Personalised Federated Learning Framework for Smart Healthcare
Rojalini Tripathy, Padmalochan Bera, Shreya Ghosh, Rajkumar Buyya
cs.LG · cs.DC
Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without centralising sensitive patient data. However, real-world healthcare federations are often characterised not only by non-IID data, but also by heterogeneous clinical objectives and partially overlapping feature spaces. Different hospitals may optimise distinct and potentially conflicting objectives, such as mortality risk prediction,...
-
33
Beyond the Gegenbauer Paradigm: q-Orthogonal Kernels for Machine Learning
Álvaro Sánchez-Paniagua Ríos, Juan P. Llerena, Alberto Lastra, Nuria Torrado, Edmundo J. Huertas
cs.LG · stat.ML
The performance of Support Vector Machines (SVMs) critically depends on the kernel function choice, which enables implicit mapping of data into high-dimensional feature spaces. While classical kernels like Radial Basis Function (RBF) remain popular, orthogonal polynomial kernels offer mathematically interpretable alternatives that can incorporate structured prior knowledge. This work extends the orthogonal polynomial kernel paradigm by...
-
34
Approximate Speculative Decoding
Yuannuo Feng, Zegang Peng, Yuxin Xie, Yubing Ye, Yizhe Chen, Wenshuai Yao, Wenyong Zhou, Wang Kang
cs.LG · cs.AI
Speculative decoding accelerates autoregressive generation by verifying a draft block with a target model in parallel. Under standard greedy verification, decoding stops at the first draft token that differs from the target argmax, discarding the remaining target-scored suffix. Although accepting such a mismatch changes the decoding trajectory, it can make a contiguous suffix reusable when its tokens remain target-greedy under the realized...
-
35
Stop Replacing Noise with Noise: Two-Source Reliability Assessment for Label Correction and Sample Reweighting in Label-Noise Learning
Wenxiao Fan, Kan Li
cs.LG · cs.CV
Refurbishment-based noisy-label learning mixes an observed label with a model-derived pseudo target, typically using one sample-wise cleanliness score to control both branches. This creates a hidden coupling: reducing trust in the observed label automatically increases trust in the pseudo target. We show that this complementarity can replace one unreliable signal with another because a pseudo target learned from corrupted supervision may...
-
36
Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces
Francesca Carlon, Vincent Ginis, Andres Algaba
cs.LG · cs.AI
Large language models often reason at length before answering, increasing cost and latency. Prompts and trained settings can shorten this reasoning, but a shorter trace may only show that the model stopped sooner. Here, we evaluate paired runs of the same question at matched reasoning horizons across 198 GPQA Diamond and 500 MMLU-Pro questions. We test a numeric/concision prompt that announces a token limit for Qwen3-14B and the trained...
-
37
TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series
Nicolas Zumarraga, Lorenzo Steno, Ning Wang, Max Rosenblattl, Thomas Kaar, Maxwell A. Xu, Kevin O'Sullivan, Markus...
cs.LG
Precise anomaly localization over long-context time series is a crucial task in monitoring applications across clinical care, industrial operations, financial services, and logistics, where brief evidence may hide inside long spans of high-frequency data. Time-Series Language Models (TSLMs) are able to ingest time series data and verbalize findings on anomalies in natural language; however, recent benchmarks report a decrease in retrieval...
-
38
Benign interpolation and Occam's razor
Tom F. Sterkenburg, Daniel A. Herrmann, Jan-Willem Romeijn
cs.LG
Contemporary deep learning methods generalize well even when they fit their training data perfectly, a phenomenon known as benign interpolation. This phenomenon cannot be accounted for by classical statistical learning theory and has prompted a range of attempted new explanations in the statistics and machine learning literature. A common feature of these new proposals is an appeal to a simplicity preference among interpolating models, often...
-
39
Tight Worst-Case Bounds for the Smallest Eigenvalue of ReLU NTK Gram Matrices
Zhao Song
cs.LG
For $n$ unit vectors $x_1,\ldots,x_n \in \mathbb{R}^d$, we study the continuous ReLU derivative Gram matrix $H$, whose entries are obtained by averaging pairwise gated inner products over a standard Gaussian direction. Writing $ Δ_\pm := \min_{i \neq j} \min\{ \|x_i-x_j\|_2, \|x_i+x_j\|_2 \} $ for their projective separation, we prove the universal dimension-free lower bound $ λ_{\min}(H) = Ω( Δ_\pm/\sqrt{\log n} ) $. Conversely, we construct...
-
40
AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning
Shengyang Li, Yiting Dong, Liuyang Song, Ximing Wang, Luyuan Xie, Cong Li, Qingni Shen, Zhaofei Yu
cs.LG · cs.NE
Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy. To facilitate practical deployment on resource-constrained edge devices, Spiking Neural Networks (SNNs) have emerged as a promising alternative to traditional Artificial Neural Networks (ANNs) due to their sparse computing mechanisms and high energy efficiency. However, jointly training ANNs and SNNs exposes a...
-
41
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
Siming Fu, Zheming Fu, Ruizhe He, Hualiang Wang, Jie Huang, Xiaoxiao Ma, Mingchen Zhong, Weihu Huang, Xiaoxuan He, Haojun Xu
cs.LG · cs.CV
On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this holds, as when the strongest teacher available and the student one wishes to deploy come from different model families, and find that the standard recipes have no answer: teacher...
-
42
Provably Learning Multi-Head Attention with Queries
Sunyeop Kim, Insung Kim, Jian Guo
cs.LG · cs.CR
We study the problem of learning multi-head softmax attention from black-box input-output access. The learner may query arbitrary real-valued token sequences and observe only the scalar output at the final token. Recent work gives an algorithm using $O(d^2)$ value queries to recover the single-head parameters $(W,v)$. For multiple heads, the same work establishes identifiability under the assumption that the heads occupy pairwise orthogonal...
-
43
The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics
Shashwat Sourav, Aishwarya Balwani
cs.LG · cs.AI · cs.CL
Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process. Existing approaches that leverage verbalized CoTs to monitor reasoning correctness, however, largely evaluate the semantic correctness or consistency of individual intermediate steps, rather than how the reasoning process evolves across the trace. As a result, failures distributed...
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.