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 246
Feature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphs
Adversarial detection on evolving attributed graphs faces two challenges: fraud labels arrive late or not at all, and natural distributional drift erodes any trained decision boundary.Universal Distributed Feature Extraction Complementary to Side Information via H-Score
This paper considers a distributed estimation system where edge nodes transmit averaged features to a center node for parameter estimation.Attention-Graph Curvature for the Verification of Mathematical Reasoning
Language models have recently solved open Erdős problems and achieved gold-medal level performance on International Mathematical Olympiad problems.Learn from Move: the Next Step for GUI Agents
Existing benchmarks for GUI agents primarily focus on increasing task difficulty by extending task horizons.Amortised adaptive importance sampling
Monte Carlo sampling algorithms aim to produce samples from a target distribution with a given unnormalised probability density function.CopyQuad: Quadrupedal Skill Transfer from a Single Side-View Video Without a Depth Model
Video-to-robot pipelines for quadrupedal imitation insert a learned lifting stage, either a monocular depth model or a per-clip 3D reconstruction, to recover the one axis a side-view camera cannot…Before Attention Sinks Form: Hidden-State Geometry Reveals and Modulates Their Formation
Attention sinks are usually studied after they have formed.NFMap: Topographic 2D Manifold Learning with Invertible Normalizing Flows
We present NFMap, a dimensionality reduction method for 2D visualisation that extends Generative Topographic Mapping (GTM) with a bijective normalizing flow.Is the Platform Part of the Measurement? A Protocol and Simulation Study for Cross-Platform Equivalence of Machine-Labelled Policy Sentiment
Comparing machine-labelled sentiment across social media platforms is now routine: differences in classifier scores between platforms are read as differences in public opinion.Separating Prompt Harmfulness from Interaction Safety via Partial Generation
LLM-based information systems need safety guardrails.Relational Learning as World Modeling
Relational learning typically predicts from a database state, but decision making asks a different question: how will that state change under an action?A Bethe-Ansatz Source of Early Token Correlations: A marginal-preserving construction for parallel proposals
Parallel token proposals need a joint law, not merely accurate token marginals.InfoVis: Unified Slide Image Generation and Editing
Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise editing within one canvas.Efficient Preconditioned Optimization Methods with Frequent Directions
Adaptive optimization methods have received considerable attention in recent years due to their strong empirical performance.TPPO: Tracking-Value PPO For Language Model Reasoning
Proximal Policy Optimization (PPO) is widely used in reinforcement learning with verifiable rewards for language-model reasoning.One-Layer Transformers Provably Learn In-Context K-Nearest Neighbor Prediction with Chain-of-Thought
Chain-of-Thought (CoT) enables transformers to solve complex reasoning tasks by generating intermediate reasoning steps.When Repeated Measurements Hurt Tabular Foundation Models
Tabular foundation models (TFMs) achieve state-of-the-art performance on IID benchmarks, but how do they respond to repeated measurements at the same inputs?Predicting Audio Popularity: A Comparative Study of Metadata and Acoustic Features Across Music and Sound Effects
This study addresses the prediction of audio popularity on an online sharing platform by leveraging both metadata and acoustic feature representations.DASS: A Solver-Adaptable Dynamic Auxiliary Search Strategy for Symbolic Regression
Symbolic regression (SR) aims to discover interpretable mathematical expressions from data and plays a key role in scientific discovery.Carve VFM: Carving Specialists out of Generalists, Automatic Task-Specific Compression of Vision Foundation Models
Vision foundation models (VFMs) provide transferable visual representations, but their inference cost limits deployment in many settings.