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 22
Theoretical Analysis of Muon on Transformers for Next-Token Prediction
Muon has recently shown strong empirical performance in training Transformer-based large language models (LLMs), yet its optimization dynamics remain poorly understood from a theoretical perspective.Hierarchical Intelligent Evolutionary Optimization for UAV-Assisted NOMA-MEC Systems
The integration of unmanned aerial vehicles (UAVs), mobile edge computing (MEC) and non-orthogonal multiple access (NOMA) provides an effective solution for computation-intensive and…KeyWise: Efficient Video-Only Piano Transcription with a Lightweight Per-Key Architecture
Audio-based piano transcription is hampered by the sustain pedal and by noisy or missing soundtracks, problems that video-only transcription avoids, since a top-view video shows directly when each…Bridging CLIP with DINO: Cross-Modal Information Maximization for Online Test-Time Adaptation
Vision-language models such as CLIP enable zero-shot classification from arbitrary class names, but under test-time corruptions, their visual encoder projects distorted features onto incorrect…Hybrid Particle-Voxel Dynamics for Multimodal 3D World Simulation
Predicting how the world evolves in response to robot actions is central to policy learning, evaluation, and planning.SKILL2STEER: One-Pass Hypernetwork for Mapping Natural-Language Skills to Low-Rank Post-Block Activation Shifts
Compiling a natural-language agent skill into model parameters removes the skill text from the prompt and leaves behind a small artifact that can be distributed and reused.Sample-Grained Approximate Unlearning with Provable Per-Sample Bounds
Machine unlearning aims to erase the influence of a designated forget set from a trained model while preserving strong utility on the retain set.Variational Learning with Lie Group Exponential Families
Variational Bayesian learning for deep neural networks offers many potential benefits.E2I-Flow: EEG-to-Image Reconstruction via Wavelet-Temporal Cross-Attention and Conditional Flow Matching
Electroencephalography (EEG)-based visual decoding and reconstruction aims to recover visual information from non-invasive brain signals.The Price of List Replicability: Tight Bounds for Bias Estimation
We study the sample complexity of list replicable algorithms for estimating the biases of $d$ coins.A Universal Raw-IQ Radar Encoder for Cross-Sensor Human Sensing
Radar-based human sensing typically relies on end-to-end task-specific models trained on hand-chosen signal projections, which generalize poorly across unseen users, tasks, and hardware.CANDO: Conservative Action-Noise Directional Optimization for Residual Reinforcement Learning
Pretrained generative policies provide strong behavior priors for robot control, but adapting them efficiently with online reinforcement learning remains difficult.CosmosAlpha: Multi-Relational Graph Search with Pareto-Guided Exploration for LLM-Driven Alpha Mining
Discovering predictive alpha factors from noisy financial data is a fundamental yet challenging problem in quantitative finance.Curriculum unlearning in humans and neural networks
During learning, humans often benefit from curricula that teach simple rules before exceptions.Ground-Wing: A Parametric 3D Wing-in-Ground-Effect Dataset for Benchmarking Neural Surrogate Models
This paper presents a CFD dataset of a highly parametrized 3D wing operating in ground effect, designed for benchmarking neural surrogate models for aerodynamic prediction, using a wing shape and…Spectral Quantum Memory for Implicit Neural Representations
Implicit neural representations (INRs) model signals as continuous functions from coordinates to values, but their performance depends strongly on how spectral capacity is allocated.Conditional independence and graphical models for rankings
Ranking models define probability distributions over rankings and are fundamental in applications such as preference learning and decision-making.Estimating "Realized" Skewness using Convolutional Neural Network
We propose a new estimator of low-frequency skewness (monthly) that exploits high-frequency data (5 min) through a direct functional mapping consisting of layers of Convolutional Neural Networks…SCANO: Restoring Boundary-Condition Completeness in Sampled Meshes with a Sliced-Cross-Attention Neural Operator for 3D Thermal Fields
Training neural operators on million-cell meshes can exceed GPU memory limits.CAPSkip: Cancellation-Aware Prefix Skipping for Selective Backpropagation
Per-step selective back-propagation forwards every example of a mini-batch but back-propagates only some of them.