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 15
A trust layer for fast pedestal-stability surrogates: calibrated error bars, out-of-distribution alarms and few-shot recalibration
Machine-learning surrogates of linear peeling-ballooning stability now run in milliseconds, but they are mostly deployed as point estimators: they do not say how wrong they may be, or when a query…The Behavioral Rate of Fine-Tuning: Compression as a Measure of Useful Information
Low-Rank Adaptation (LoRA) adapts a frozen language model through a compact learned update, making it a natural setting for asking how much information fine-tuning needs to write.Verifier-Guided Self-Consistency: Test-Time Reasoning with Imperfect Generators and Verifiers
Large language models can solve many multi-step reasoning problems, but their reasoning remains brittle: plausible intermediate steps often lead to incorrect answers.Alternatives to Shallow Autoencoders for Collaborative Filtering
Collaborative filtering (CF) is a cornerstone of recommender systems and plays a relevant role in many modern applications.From Reconstruction to Imputation: Test-Time Optimization for Missing Time-Series Channels
Complete sensor-channel failures create a difficult form of time-series missingness: local interpolation is unavailable, and deploying a separately trained imputer for every failure pattern may be…Dimension-Free Private Mean Estimation is Impossible Without the Covariance
We study the limits of differentially private Gaussian mean estimation when the covariance matrix is unknown.Interactive World Simulation with Cosmos for Physical AI
We present a shared framework that adapts Cosmos world foundation models for real-time interactive world simulation in Physical AI.Noise-regularized training of quantum circuit Born machines under a finite shot budget
Quantum circuit Born machines (QCBMs) can learn distributions that are hard to sample from classically, but their value depends on generalizing from finite training data.TestBED: An Open-Source Toolkit for Bayesian Experimental Design
Bayesian experimental design (BED) is a principled framework for intelligent data acquisition with applications across a wide range of scientific and industrial domains.Detecting Silent Action-Interface Mismatch with Calibrated Relational World Models
A robot action can satisfy shape and range constraints yet carry the wrong semantics: axes may be permuted, signs inverted, rotations rescaled, or gripper polarity reversed.Fingerprinting the Dispatchers behind Distributed Model Extraction
API distillation campaigns try to hide model-stealing traffic by splitting requests across thousands of load-balanced accounts, which standard content classifiers often miss.Self-Directed Apple Tasting
We study the classical apple-tasting setting, a partial feedback model in which the learner observes the true label only when it predicts $1$.Do unlearning algorithms learn the right features?
Machine unlearning is commonly evaluated with standard post-deletion metrics that compare an unlearned model to one retrained on the remaining data.SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents
Tool-using large language model (LLM) agents translate model outputs into consequential actions, turning indirect prompt injection into an execution-security problem.Don't Replace, Complement: A Detector-Agnostic Subspace Signal for Near-OOD Detection
Post-hoc out-of-distribution (OOD) detection is mature on far-OOD yet remains weak on near-OOD.PINR-ESI: Physics-Informed Self-Supervised Implicit Neural Representation Framework for EEG Extended-Source Imaging
EEG extended-source imaging aims to localize active cortical regions and characterize their spatial extent, yet supervised inverse networks typically depend on synthetic EEG-source pairs and may be…Where It Breaks: Diagnosing Perception, Memory, and Decision Failures of a Vision-Language Agent in Pac-Man
Training an agent to play Pac-Man with only up, down, left and right actions raises a basic question: when performance is poor, what should be improved?ALTO: African and Levantine Tech-Facilitated Gender-Based Violence Corpus
Tech-facilitated gender based violence (TFGBV) is a pervasive online harm affecting women and gender minority groups through its many direct and covert forms.Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching
Deep generative models, particularly Flow Matching frameworks, have emerged as powerful tools for synthesizing complex physical systems.Symmetry Breaking at the Edge of Stability via Central Flow Analysis
Continuous symmetries in neural networks lead to conserved quantities that are invariant under gradient flow, such as layer balancedness in linear and ReLU networks.