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 104
High-resolution tactile observation makes hidden racket-control mechanisms learnable
Experts can master fine hand-object manipulation skills, yet limited conscious perception of rapid tactile interactions hinders their ability to articulate the underlying control mechanisms.ExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess Calibration
We introduce ExCal, a normal-only multivariate time series anomaly detector that combines raw state retrieval, a signal/derivative subspace, and robust statistics across temporal scales.Distributed Predictive Flocking for a Swarm of Miniature Vibration-Driven Robots in a Confined Arena
Coordinating many miniature robots in a confined arena, with no leader, central planner, or global map, is a core challenge for swarm robotics.Linear Probes Transfer from Base to Distilled Language Models despite Rotation
Linear probes, classifiers that read a language model's internal activations, are widely used to detect harmful requests.ArchiveLens: A Generative Spatial Knowledge Framework for Semantic Reconstruction of Historical Maps
Historical maps contain dense morphological and semantic information about past urban environments, but many digitization workflows focus primarily on extracting geometry, and do not capture…Making Reasoning Visible: Configuration-Aware Diagnostic Modeling for Adaptive Scaffolding in Structured Reasoning Tasks
Modeling the latent, multi-step reasoning processes of learners is a core challenge for adaptive tutoring systems, which often rely on simple right/wrong answers rather than understanding how…Distilling neural networks into equations to predict planetary instability
The problem of predicting when a multi-planet system will become dynamically unstable has defied analytical progress over the past three hundred years.Adversary Brains: Hypothesis-Based Logical Signatures for Threat Actor Detection with LLMs
An adversary brain is an LLM-based model of a threat actor's behavior, held as an evolving logical signature: a hypothesis with enough structure that data can test it continuously, without a person…Adapt for Planning, Not just Prediction: Optimistic Test-Time World Model Adaptation
Latent world models are typically pre-trained offline and kept frozen at test time, so planning with them can degrade under distribution shift.Proofs of strong forms of the Bovdi--Geche universality conjecture and a complex analogue
We prove two universality theorems for neural networks consisting of a single neuron.TRON: Transferring Naturally Evolved Network Architectures into Neuroevolution
Neural architecture search (NAS) is challenging because of the vast, non-linear space of artificial neural network (ANN) topologies.Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel
Many high-throughput scientific experiments produce distributional outputs, requiring conditional generative models to interpret the data, and to predict outcomes at new inputs.Provably Efficient Q-learning for Robust Reinforcement Learning
Standard reinforcement learning (RL) algorithms based on Markov Decision Processes (MDPs) are vulnerable to sim-to-real gaps.A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis
Aviation authorities hold decades of accident reports whose narratives record how investigators reconstructed each accident.SCAFFOLD under Hessian Similarity: Sharp Convergence Rates
One of the main challenges of federated learning is heterogeneous data split among the clients, leading to biased local updates called client drift.CounterFlow: Target-Conditioned Flow Matching for Visual Counterfactuals
In eXplainable AI, counterfactual explanations have gained significant traction by offering users direct, intuitive, and actionable insights into model decisions.GNN-VIEW: Visual Inspection and Explanation of Graph-based Earth-System Models
Machine learning Earth-system models are becoming increasingly important, and so is their development.MiRL: Error-Targeted Reinforcement Learning for Correcting Terminal Agent Misbehaviors
Error-targeted learning gives a legible way to improve a model: identify specific weaknesses of the model, train the model to fix these weaknesses, and check whether the weaknesses are fixed.Triage: Skip, Skim, or Refine Attention Tiles in Video Diffusion Transformers
Attention over tens of thousands of visual tokens dominates the inference of video diffusion transformers (DiTs).Detecting bus delays and service anomalies in Niterói with autoencoder latent feature representations
Bus riders judge service by two failures: single trips that run late, and days on which the whole system misbehaves.