AI & Machine Learning · Computer Science & AI
Machine Learning
The newest papers in Machine Learning that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 12 October 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Machine Learning every morning.
Follow Machine Learning and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 240
SPELUNKA: A Framework for Finding Unanticipated Associations in Vision-Language Models
Vision-Language Models (VLMs) are the backbone of many state-of-the-art multimodal systems, but often encode spurious and harmful associations from their training data.A 4-Qubit Variational Quantum Classifier for Sequence-Specific Classification of DNMT3A and DNMT3B Flanking Methylation Preferences
DNA methylation is a critical epigenetic modification that regulates gene expression and genome stability, primarily catalyzed by the DNA methyltransferase 3 (DNMT3) family of enzymes.Improving the Evaluation of Biomedical Question Answering with Few Human Preference Signals
Retrieval-Augmented Generation (RAG) systems are increasingly used for biomedical Question Answering (QA).Certified Robustness via Sparse Second-Order Cone Relaxations
Certified robustness is critical for deploying neural networks in safety-sensitive settings, but computing exact certificates typically requires solving nonconvex optimization problems.When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits
Layer-wise post-training quantization methods let each layer compensate for the quantization error inherited from earlier layers.Limit Theory for Online Expectile Estimation under Short and Long Range Dependence
Expectiles are tail-sensitive distributional summaries with important applications in financial risk measurement and forecasting, yet statistical theory for their online estimation from dependent…A Nonlinear Time-Series Theory for Constant-step SGD with Momentum
Constant-step stochastic gradient descent with momentum (SGDM) augments the parameter recursion with a momentum state that carries geometrically decaying memory of past stochastic gradients.CLNO: Conservative Local Neural Operator for Compressible Flow Prediction
We propose a conservative local neural operator (CLNO) for accurate and generalizable autoregressive prediction of compressible flows.Autoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM Generation
Large language models (LLMs) have achieved remarkable success across a wide range of language tasks.Backward Conformal Prediction under Covariate Shift
Backward conformal prediction (BCP) fixes the size of a prediction set and estimates its miscoverage, but assumes calibration and test data are exchangeable.How the Classical Baseline Shapes Machine-Learning Speed Claims in Topology Optimization
Topology optimization places material so that a structure resists deformation under given loads.Interpretable Graph Partitioning for Spatial Prediction
Spatial prediction estimates unobserved values from spatially distributed observations.Understanding and Reducing Misalignment in Persuasion Optimization
Frontier models are now trained for complex multi-agent tasks, from running a company to engaging in negotiations.Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems
Reliable deployment of LLM-based multi-agent systems calls for runtime auditors that predict terminal outcomes from observed execution prefixes.Beyond Single-Pathogen Forecasts: Predicting Shared Respiratory Hospital Burden from Influenza, COVID-19, and RSV
Co-circulating influenza, COVID-19, and respiratory syncytial virus (RSV) create a shared hospital-admission burden, because beds, staff, testing capacity, and respiratory support are allocated to…Regime-Aware Router Learning for Multi-Domain Medical Image Generation with Diffusion Experts
Heterogeneous medical image data motivate domain-specialized diffusion experts, but expert specialization alone does not determine how their predictions should be combined during sampling.Memorization in image classification: test set behavior and scaling laws
Deep neural networks are capable of both learning generalizing solutions on natural tasks and memorizing arbitrary mappings.CloneOT: predicting clone-specific perturbation responses with lineage-supervised neural inverse optimal transport
Predicting single-cell perturbation responses requires mapping between two unpaired populations of cells measured before and after the perturbation.SelectTTRL: Representation-Guided Data Selection for Efficient Test-Time Reinforcement Learning
Test-Time Reinforcement Learning (TTRL) enables large language models to adapt directly on unlabeled test problems by constructing pseudo-labels from multiple sampled responses.Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR
Reinforcement learning with verifiable rewards (RLVR) typically uses small rollout groups per prompt, where repeated sampling from the same policy can yield highly similar trajectories, reducing…