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 26
Beyond Foundation Models: PFN Priors Improve Tabular Hyperparameter Optimization
Synthetic priors have so far served one purpose: pretraining tabular foundation models.Macrocanonical Generator Networks: Data-Efficient Neural Surrogates for Amortized Physics Simulation
Many scientific simulations are computationally expensive, limiting their use in simulation-based inference, uncertainty quantification, and decision making.Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional Understanding
Vision-language verifiers judge whether an image faithfully matches a textual description, yet existing training pipelines typically rely on static supervision from stronger external judges or…Basin2Vec: Learning Basin-Centric Embeddings for Scalable Hydrological Modeling
Reliable streamflow prediction across time and in ungauged basins requires representations that capture hydrologically relevant basin characteristics.Learning Behaviorally Relevant Dynamics in Multimodal Neural Recordings
Multimodal neural data can enable a more complete understanding of brain dynamics underlying behavior.Provably Learning Mixtures of Linear Experts
Mixture-of-Experts (MoE) models are widely deployed in modern machine learning.Stepsize modulation for cross entropy from local quadratic optimization
Two methods are presented that perturb a given learning rate schedule in stochastic gradient descent with cross entropy loss.Ensembles of Random Partition-Based Models under Covariate Shift
Distribution shifts, including covariate shifts, are ubiquitous in real-world applications of machine learning.Empirical Bayes Flow Matching for Continuous Cryo-EM Heterogeneity
We address the problem of learning generative priors over high-dimensional latent variables from indirect, noisy observations, with a focus on continuous heterogeneity in cryo-electron microscopy…Multi-Objective Generative Optimization via Expected Hypervolume Fine-Tuning
Scientific discovery requires plausible designs spanning useful trade-offs among competing properties: a molecule with strong binding affinity, for example, may be difficult to synthesize.Privacy for Free in Efficient Agnostic Halfspace Learning
We provide the first computationally efficient, differentially private algorithms for agnostically learning halfspaces.Physics-informed traditional and generative Mori-Zwanzig-reduced models for multiscale systems
Model reduction via the Mori-Zwanzig (MZ) formalism is well understood for coarse-grained representations constructed from standard basis functions such as Fourier functions.Fusing Earth observation embeddings and spaceborne terrain with meteorological forcing for flood peak depth prediction from high-water marks
Flood peak depth on normally dry land governs damage and risk to life, but is observed only sparsely, by post-event high-water mark (HWM) surveys, and depth derived from satellite flood extent is…Fairness Metrics based on the AUC in Clinical Predictive AI
Fairness evaluation of clinical prediction models for binary outcomes often involves fairness metrics that compare the area under the receiver operating characteristic curve (AUC, or c-statistic)…PLANTEUR: A Crop-Type Segmentation Benchmark for Tropical Regions
We introduce PLANTEUR, a benchmark for crop-type mapping from satellite images in the French overseas territories.Learning curves in natural and artificial systems
A general mathematical model of experience formation is considered, in which the learning level is defined as the probability that the next value of the uncertainty factor has already been mastered…Post-Inference Model Chaining: A Problem Statement and a Model-based Bootstrap for Training End-to-End Digital Twins
End-to-end digital twins can be constructed by fitting separate stage models and connecting them after inference.Regret-based Characterization, Information Limits, and the Sample Complexity of Auditing Adaptive Policies
A policy can earn its performance by where it locates on average or by reacting to information.Post-stratified importance sampling
Importance sampling is a building block of modern statistical computing, but the weighted estimate is prone to high or infinite variance.Shrinkage prior for implicit generative models
Implicit generative models based on deep neural networks have revolutionized many scientific fields, from weather research to language generation.