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 219
Training Language Models to Fail Gracefully
Reinforcement learning makes language models better at solving tasks, but the same mechanism also rewards guessing.Posterior Frequencies and the Cost of Not Fitting: A Correction to a Memorization Lower Bound
Feldman's memorization lower bound assigns a frequency coefficient based on how often a point appears in the training sample.Hyperspherical Contrastive Representations Unlock Planning and Exploration
We develop a self-supervised reinforcement learning algorithm that learns to build towers of up to eight cubes from scratch, without prior data, rewards, demonstrations, or pretrained models.When Does Momentum Help in Reinforcement Learning with Verifiable Rewards?
Momentum is a classical tool for accelerating convex optimization and a standard component of modern large language model training.One Size Does Not Fit All: Curvature-Aware Adaptive Perturbation for SAM
Poor generalisation in deep neural networks is frequently associated with convergence to sharp minima.Tracking a Small Set of Experts in Online Convex Optimization
For the fundamental problem of prediction from expert advice, Freund asked whether one could compete with a comparator that switches $k$ times among only $m$ experts.OrionMoE-v1.0: A Mixture-of-Experts Foundation Model for Tabular In-Context Learning
Tabular foundation models enable in-context learning by predicting unseen observations from a labeled support table without task-specific parameter updates.Continual Learning for Reliable In-Sequence Molecular Communication
This paper considers reliable in-sequence molecular communication, where bio-nanomachines exchange molecule-encoded information in a specified order, and investigates a new simulation-based method…The Accuracy Well: Nonmonotone Accuracy Dynamics at Vanishing Initialization
We study classification dynamics under small initialization and identify a pronounced non-monotone behavior of accuracy that we call the accuracy well: accuracy rises rapidly early in training…What Does Disagreement Mean? A Semantic Identifiability Frontier for Pairwise Preference Learning
Pairwise comparison data are a standard supervision signal in preference learning, but disagreement in such data can reflect stable latent heterogeneity, ephemeral stochasticity, or non-binary…The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation
The scaling relationship of compute and performance for language models (LMs) has been extensively studied; more recently, models are being designed to scale memory use, as well.Learning by Examples: Power Grid Steady State Analysis with a Tabular Foundation Model
Foundation models have shown strong generalization across scientific domains, but their use in power systems remains largely task-specific.Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning
Value-based Q-learning for continuous control can discretise the action space, but the resolution of the discretisation trades early exploration against final precision.SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift
Opponent histories can mislead after behavioral shifts.Lost in Translation: Why Lower Bias Scores Don't Mean Fairer Models
Bias audits of multilingual language models usually compare a model's average stereotype score in English with its average in another language and read the difference as a difference in fairness.Decoupled Marginal Sharpening for Training-Free Inference-Time Scaling
We study how to improve LLM reasoning at inference time without updating model weights or using external reward models.Average-Reward Policy Identification from a Single Continuing Trajectory
In reinforcement learning, an agent must explore an unknown environment to learn how to make good decisions.Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling
Reinforcement learning with verifiable rewards (RLVR) trains language models from checked task outcomes, but assigning a terminal reward to individual reasoning tokens or actions remains difficult.Graph-Enhanced Disease Trajectory Discovery and Temporal Endpoint Forecasting from Longitudinal Electronic Health Records
Longitudinal electronic health records (EHRs) can reveal disease-progression structure, while useful forecasting requires leakage-controlled discovery, censor-aware outcomes, and inspectable…VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution
Generative super-resolution (SR) can recover sharp detail in computed tomography (CT) images from severely downsampled observations, but the missing high-frequency content is not uniquely determined…