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 216
Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration bounds
We study the minimax estimation of the pseudo-spectral gap $γ_{ps}$ of a Markov chain from the observation of a single trajectory.Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL
Scaling self-supervised contrastive reinforcement learning (CRL) to 1000-layer Euclidean neural networks has enabled state-of-the-art goal-reaching performance, yet wall-clock time scales linearly…ChemArgus: Automated Scientific Diagnostics for Lab-Grade Multimodal Chemistry Reasoning: A Frontier Benchmark
Chemistry evaluation has moved past multiple-choice probes toward open-ended expert problems, yet the benchmarks that define the current frontier still score answer endpoints alone.On the Convergence of Semi-Gradient TD: A Mean Field Perspective
Semi-gradient temporal-difference learning is a core algorithmic component of reinforcement learning, but bootstrapping with function approximation generally induces a non-conservative vector field…Weighted Adjoint Matching: Finetuning Flow Matching Models with Time-Dependent Control Cost
We introduce Weighted Adjoint Matching, a method to finetune a pretrained diffusion or flow matching model given a differentiable reward.Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter
A staged physics-informed neural network (PINN) is proposed for identifying the inductance, capacitance and parasitic resistances of a DC buck converter from time-domain data.GBTSVR: Twin Support Vector Regression via Granular Ball Computing
Regression models used in real-world applications are often challenged by noise, outliers, data heterogeneity, and asymmetric error characteristics, which severely limit the effectiveness of…Trainable at Depth, Solvable at Small Size: What the Loss Surface of a Polynomial Activation Dictates for Designing, Initializing and Training Networks
What makes a deep network train, and what shape is its loss surface?Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow
MeanFlow predicts interval-average velocities, but conventional few-step sampling ties the interval queried from the model to the duration of the state update.A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization
Federated learning over decentralized networks inherently trades off the suppression of local finite-sample noise through collaboration against the bias that collaboration introduces between…What Do Foundation Models for Market Microstructure Learn? A Controlled Study with Synthetic Limit Order Books
Autoregressive transformers trained on limit order book (LOB) message streams are increasingly proposed as foundation models for market microstructure.Exhaustive Canonical Skeletons Generation: A Formal Dataset for Decomposable Symbolic Regression
Neural symbolic regression (SR) models require diverse datasets of mathematical expressions for robust training.From Spectral to Frobenius: When Muon Loses Its Spectral Implicit Bias
Prior work on implicit bias shows that gradient descent selects the Frobenius max-margin direction on linearly separable problems, whereas Fan et al. (2025) established spectral max-margin behavior…KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks
KANLab is a browser-based visualization tool designed to interactively teach the core concepts of Kolmogorov-Arnold Networks (KAN), forked from the widely successful TensorFlow Playground.A Bregman Proximal Viewpoint on Neural Operators
We present several advances on neural operators by viewing the action of operator layers as the minimizers of Bregman regularized optimization problems over Banach function spaces.Seeing at the Edge: Energy Characterization of Vision-Language Model Inference on Edge Platforms
Vision-language models (VLMs) are moving onto edge devices, but little is known about how much energy they draw on single-board computers with NPU or GPU accelerators, or where that energy goes.In-Context Batch Black-box Optimization via Flow Matching
Batch black-box optimization is important for expensive systems where many candidates can be evaluated in parallel, yet only a few rounds of evaluation are affordable.Gap Detection: Mitigating Homogenization through Demand and Defensibility
Language models often produce semantically similar answers to open-ended questions, even when many plausible alternatives exist.Optimizing Sparse Boolean Rule Networks using Mixed Integer Linear Programming
We study the problem of learning accurate and cognitively simple binary classifiers that are directly interpretable as Boolean rules.RM-OPD: On-Policy Distillation for Generative Reward Models
Reinforcement Learning on Mixed-domain preference data (Mix-RL) has become the mainstream approach for training general-purpose Generative Reward Models (GRMs).