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 227
Train for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning
Multi-sample reasoning measures candidate coverage, the probability that at least one of $K$ candidates is correct.HiSTOR: Structured Treatment-outcome Representation Learning for High-Dimensional Longitudinal Data
Estimating potential outcomes under alternative treatment sequences is essential for personalized decision-making, but remains challenging with high-dimensional covariates and time-varying…Geometric Structure Predicts Per-Example Neighborhood Loss Under PCA Truncation
Dimensionality reduction can preserve the average performance of text embeddings even when a substantial fraction of their dimensions is removed.Auditing Failure Attribution: Label Predictability and Judge Behavior
Failure-attribution benchmarks ask an LLM judge which step or agent caused a failure.Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
Large language model (LLM)-based multi-agent systems (MAS) are commonly organized around two coordination regimes.Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback
Gaussian process bandits exploit similarities among configurations to optimize prompts, retrieval systems, and agent workflows.Hybrid Parallel Bessel KAN Model: a Kolmogorov Arnold Network: integrated framework for developing a novel architecture to reconstruct the fused-basis approach via a parameter free quadratic interaction
The Kolmogorov-Arnold Network (KAN) challenges traditional MLPs by placing learnable activation functions on network edges.Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis
We study industrial fault diagnosis as a classification task that assigns sensor time-series windows to predefined health states or fault types.Posterior-Averaged Bellman Flow Matching for Distributional Critics
Distributional critics model the full return distribution, providing richer signals for exploration and risk-sensitive control.GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation
Contextual forecasting seeks to improve time series forecasting by incorporating forward-looking information, such as planned events, external conditions, and expert expectations.Beyond the End-Effector: Learning Whole-Arm Contact Manipulation from Human Demonstrations
Robot manipulation has traditionally relied on end-effector-centric interactions.Learning from fracture: Teaching language models to design through physical experience
How can language models learn to optimize physical designs through experience?SPARCL: Spatially Adaptive Regional Coverage for Active Learning in Chest X-ray Analysis
Pixel-level annotation for chest X-ray (CXR) lesion segmentation is expensive, making active learning (AL) essential.Follow the Perturbed Leader for Linear Bandits: $\sqrt{T}$ Regret over General Action Sets
We give the first adversarial linear bandit algorithm based on Follow-the-Perturbed-Leader (FTPL) that achieves $\sqrt{T}$ regret over general action sets.Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR
Reinforcement learning with verifiable rewards (RLVR) has become a principal recipe for improving the reasoning of large language models (LLMs).Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design
Materials and chemical optimization must choose the next synthesis, characterization, or high-fidelity simulation from sequential observations under a limited budget.A Tutorial on Quantum Amplitude Embedding with Data Re-Uploading
Amplitude embedding lets a variational quantum model read many classical features with few qubits, but the model output is then only a quadratic form in the normalized input.FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion Retrieval
Evaluating fashion retrieval systems remains challenging due to the limited availability of benchmarks that capture the fine-grained, open-ended queries encountered in real-world search and…GeoNIRS: Geometry-Aware Pretraining for Heterogeneous fNIRS Representation Learning
Functional near-infrared spectroscopy (fNIRS) provides portable and spatially localized measurements of cortical hemodynamics, but differences in channel count, probe layout, signal distribution…Persistence Positional Encoding: A Minimal Transformer Recipe for Persistence Diagrams
Persistence diagrams (PDs) represent multiscale topological information as multisets of birth-death pairs $(b,d)$.