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 58
Geometry of Confabulation and Refusal in Small Language Models
Faced with an unanswerable question, small language models can either refuse or confabulate: confidently produce a wrong answer.[Re] Pure Noise to the Rescue of Insufficient Data
We examine the main claims of Zada, Benou, and Irani (2021), which states that in an image classification task with imbalanced training data, (i) using pure noise to augment minority-class images…Best-of-Both-Worlds FTRL for Linear Bandits: The Interplay of Information Acquisition, Corruption, and Geometry
We study \textit{best-of-both-worlds} (BOBW) algorithms for linear bandits, which aim to simultaneously guarantee $\gO(\sqrt T)$ regret in the adversarial regime and $\gO(\log T)$ regret in the…Accelerating posterior sampling in Bayesian inverse problems with diffusion models: an online-offline perspective
Bayesian inverse problems require both informative prior models and computationally feasible posterior inference.When Does Exploration Prevent Collapse? Three Regimes and the Path of the Reward in Self-Consistency Training
Test-time reinforcement learning (TTRL) adapts a model without labels by rewarding answers that agree with the majority, but it collapses the policy onto its majority answer and can remove the…Accuracy Is Not Risk: Why Medical AI Should Not Report Only Its Most Likely Label
Many medical AI models are trained to reproduce a single reference label and hand the most likely label to the next step in a clinical workflow.Are Fake Citations a Form of Reward Hacking? A Pre-Registered Study of Post-Training and Citation Cues
Post-trained language models fabricate citations at high rates.Hidden selection rules and amplitude ceilings in quantum Fourier models
Quantum models with Pauli data encodings compute trigonometric polynomials whatever channels, ancillas and outcome-averaged measurements follow, so their expressivity depends on the Fourier…AgentCBO: Causal Belief Routing for Bayesian Optimization under Unknown Graphs
Causal Bayesian optimization (CBO) typically relies on the unrealistic assumption of a perfectly known causal graph.Inferring missing locations in human mobility data using memory effects
Empirical datasets used to characterize human mobility are sparse in space and time, owing to technological factors such as coverage and battery, or to the erratic nature of online interactions.Alignment Flywheel-Guided Suppression Patching for Interactionless Inverse Reinforcement Learning
Learned reward models allow reinforcement-learning agents to use demonstrations, implicit feedback, safety constraints, social norms, or other sources that do not provide a complete hand-designed…Same Function, Different Mechanism: Implementation-Local Geometry Beyond Accuracy
Two models can make exactly the same predictions yet respond differently when their implementations are perturbed.The Verifier Is Part of the Simulator: Evidence-View Gaming in Agentic Equation Discovery
A growing number of agentic pipelines search for governing equations: an agent proposes laws and a verifier checks them against simulated trajectories.Profile-aware diagnostics of discarded parameter-Hessian mass
Evaluating block-diagonal curvature models involves two questions: how much curvature they omit, and what a specific correction changes at a finite step.MoEDDI: Semantic Mixtures of Experts for Long Tailed Drug Drug Interaction Prediction
Descriptor-based drug--drug interaction (DDI) models typically apply a single global predictor despite heterogeneous physicochemical evidence and severely long-tailed labels.Unified dynamics of training, learning, inference, and reinforcement in neural networks
Through nine nanoGPT experiments, we established training-learning-inference relations: realized updates elicit state-dependent finite-amplitude responses; learning persistently reorganizes…MAPLE: A Multimodal Mobile Agent with Playbook-Learned Experience
Autonomous agents powered by vision-language models (VLMs) show great potential in navigating mobile graphical user interfaces (GUIs) to complete complex tasks.FACET: Feasibility-Automaton Complete Enumeration and Truncation-Free Scoring of Molecular Formulas from MS/MS
Determining the neutral molecular formula of a precursor ion from its tandem mass (MS/MS) spectrum is the first step in identifying an unknown small molecule.Infinite Quantiles Inference under Local Differential Privacy
We study simultaneous quantile inference under local differential privacy for a number of target probabilities that grows with the sample size.Learned Surrogates of Three-Dimensional Magnetohydrodynamic Turbulence
Three-dimensional magnetohydrodynamic (MHD) turbulence, the flow of astrophysical and fusion plasmas, is costly to simulate.