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 203
Learning Rewards in Strategic Games
Understanding the objectives that drive agents' behavior is crucial in strategic environments, where multiple agents interact and adapt to one another.The Lagrangian Structure of Cost-Penalized Active Feature Acquisition
Active Feature Acquisition (AFA) sequentially selects features to maximize predictive accuracy under an acquisition budget.SelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted Networks
Tabular foundation models based on prior-data fitted networks (PFNs) predict on a new data set in a single forward pass, but they cannot report which inputs their predictions depend on.ChronoSheaf: Joint Spatio-Temporal Spectral Filtering on Cellular Sheaves
Sheaf neural networks generalize graph neural networks by assigning each edge a learned linear restriction map that specifies how the local representations of adjacent nodes relate to one another…Why Shallow Neural Networks Learn Sinusoidal Components First: An Orthogonal Polynomial Dynamics Framework
Neural networks often learn low-frequency components before high-frequency ones --- a phenomenon called spectral bias or termed F-principle.Uncertainty-Aware Federated Learning for Joint Communication and Computation in XR Systems
The convergence of communication and computation, empowered by artificial intelligence (AI) enhanced capabilities, emerges as a key enabler for realizing the promising functionalities of the…Time to Fake It: Continual Machine Learning Intensifies Unfairness in Deepfake Detection
Deepfake detectors safeguard against misinformation, rendering their failures as much a societal as a technical concern.Learn Only Where You Can't Compute: Structured Corrections to Gaussian Process Posteriors
Physics-informed Gaussian processes (GPs) provide a principled framework for scientific inference by expressing uncertainty over empirical measurements, boundary conditions, and governing equations.P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document Parsing
End-to-end full-page document parsing must preserve the content and structure of heterogeneous elements, yet otherwise accurate outputs can contain local errors and omissions.Deep Learning of Topological Equivalence Classes
We demonstrate an application of deep learning to the problem of identifying whether two generating vectors correspond to topologically equivalent finite group actions on Riemann surfaces, showing…OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological Abstraction
Learning from experience requires recovering reusable knowledge and determining when it applies to a new situation.Interfaces and Modules: A Scalable Representation for Weight-Space Learning across Architectures
Weight-space learning across architectures requires representations that respect parameter symmetries and scale to large networks.Stateful Testing for Deep Learning Compilers
Modern deep learning compilers compile models lazily and cache artifacts across invocations.GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers
Longitudinal electronic health records (EHRs) contain complementary diagnostic and laboratory information about patient health.Close Enough is Nowhere Near: Fidelity-Consumability Decoupling in KV Caches
Multi-agent LLM systems communicate in text, which is lossy and wasteful: the sender throws away the reading it already did.Priming Base Models for Agentic Post-Training: An Open Midtraining Recipe
Frontier models, general-purpose and domain-specific alike, now include a midtraining stage between pretraining and post-training, but little has been published about how this stage is built.DemoStream: Batched Task-and-Motion-Plan Optimization for Automated Learning from Demonstration
Learning from demonstration is an effective strategy for endowing robots with manipulation capabilities but requires training on datasets comprised of massive amounts of demonstrations.Not All Unlabeled Data Are Equal: Unlabeled Data Selection for Semi-Supervised QSAR Modeling with Large Chemical Repositories
Semi-supervised learning (SSL) is particularly attractive in domains where labels are expensive to obtain, while unlabeled examples are readily available.Augment the Cache, Replace the Activation: A 2x2 Study of Internal-State Sharing
Multi-agent systems built from frozen language models communicate through text, which discards the internal state the sender already computed and makes the receiver pay to rebuild it.Selection Is Not Learning: Choosing Model Futures
Self-evolving language models train on tasks they generate, so every round must decide which updated model the next round inherits.