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 77
Unsupervised Feature Selection Using Local Intrinsic Dimensionality -- Extended Version
High dimensionality degrades both the efficiency and the effectiveness of learning algorithms, and in many applications no class labels are available to guide dimensionality reduction.Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use
A capable voice assistant must do more than recognize words; it must understand requests, reason over context, sustain conversations, and act through tools.Certified Behavioral Retention for Continual Adaptation with Held-Out Anchors
Continual adaptation requires deciding not only how to update a model, but whether to commit an update without exceeding a declared budget for changes to protected behavior.Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses
Effective computer-use agents (CUAs) should seamlessly combine visual GUI interaction with code and terminal execution within a single policy.Combinatorial Residual Network: a decay-chain-aware classifier without explicit jet assignment
Final states with several jets from the decays of heavy particles pose a combinatorial problem, since the jets must be assigned, at least implicitly, to their parent particles.AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn
Humans and animals have a unique capacity to generalize and learn in novel circumstances, including "0-shot" inference (ZI) and continual learning (CL) -- two powerful cognitive abilities.TAPE: Learning General Audio Effect Representations
Musicians and mixing engineers often can decipher the signal processing chain they hear on a reference recording, then adapt it to new material.From Teleoperation to Long-Horizon Dexterity: Evaluating Visuomotor Skills and Offline Proxies for Dexterous Manipulation
Imitation learning policies are intended to make robotic manipulation robust to variations in object pose, appearance, and environment that challenge pre-programmed motion.Predictive Maintenance at the Edge: An Embedded Anomaly Detection Pipeline Trained with Quantum Optimization
This article presents a predictive-maintenance pipeline that detects anomalies in bearings from vibration signals, adapted for deployment at the edge on low-cost microcontrollers, and that uses…Frozen in Time: How a Physics Foundation Model Forgets Under Sim-to-Real Adaptation
Scientific foundation models (SciFMs) have achieved remarkable performance on a wide range of PDEs, including the ability to efficiently adapt to unseen data distributions with additional finetuning.FARO: Function-Space Adaptive Return-to-Risk Optimization via Cross-Block Equal-Risk-Contribution Budget Allocation
Training a large language model is compute-bound, and current recipes divide the work between optimizers by hand: orthogonalized momentum for attention and MLP matrices, Adam-style updates for the…Near-Optimal First-Order Regret for Bandits with Feedback Graphs
We study first-order regret guarantees for adversarial bandits with a fixed, known directed feedback graph.GraphTFactor: A graph-based approach for proteins transcription factor prediction
Transcription factors (TFs) play an important role in regulating gene expression, making their identification a fundamental task in computational biology.TensorSSM: Memorizing Spatial Position in Dynamic State Space for Tensor Core Generation
High-dimensional tensors are ubiquitous in real-world applications but lead to massive storage overhead.Robust-by-Design Distributional Learning from Contaminated Samples
Modern data analysis pipelines increasingly rely on large datasets assembled through retrieval, scraping, automated filtering, and post-hoc curation, where the observed sample is often a…AquaProbe: Efficient Adaptation of Frozen Vision Models for Underwater Images
Reliable visual perception is essential for safe autonomous underwater exploration.TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research
As publications and products on time series forecasting (TSF) proliferate, researchers face a growing burden of analyzing existing work.No Channels Left Behind: Understanding Diffusion Acceleration through Residual Gates
Training acceleration methods for diffusion transformers, such as REPA and dispersive regularization, are commonly explained by additional supervision, spatial-structure priors, or improved feature…Learning Stabilizing Latent Feedback Controllers via Multi-Step Backward Losses
Can learned latent dynamics models support the design of feedback controllers that provably stabilize the original system?A Theoretical Framework for Understanding and Building "Any-task inference" Capable Foundation Models
In this work, we provide a formal framework and mathematical definition for the subset of foundation models focused on enabling the property of "any-task inference" (ATI) (similar to zero-shot…