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 101
STeP-TS: Shared Temporal Filters with Pruning for Time Series
Multivariate time series forecasting requires capturing temporal dependencies across multiple scales while accounting for both shared and variable-specific dynamics.TUON: A Tensor-Aware Optimizer Utilizing Tensor-SVD and Polarization for Large Language Model Pretraining
Large scale language model~(LLM) pretraining is increasingly bottlenecked by optimizer efficiency, driving optimizer design from vector-aware methods such as AdamW to matrix-aware methods.Realizing Low-Precision Storage and Sparse Execution in a Folded FPGA Speech Enhancer
Hardware-aware training often optimizes FPGA resources, latency, or bit operations, but folding changes what compression saves: shared arithmetic decouples precision, weight storage, and scheduled…Locked In: Multi-Objective RL for the AI Data Center Build-Out
AI data center build-out is a multi-trillion-dollar, multi-decade infrastructure program.Sequential versus fully conditional specification for tree-based synthesis of health data
Disseminating synthetic data in place of original ones is a promising way to enforce privacy while complying with open science principles, especially in the healthcare domain.Accelerating SO(2)-Equivariant Materials Models through Low-Precision Emulation
Rotationally equivariant architectures improve the physical fidelity of machine-learned (ML) universal materials models based on graph neural networks (GNNs).Biology-Guided Context-Aware Residual Propagation for Spatial Gene Expression Prediction from Histology
Spatial transcriptomics provides spatially resolved molecular profiling, but its cost, limited throughput and experimental complexity hinder routine large-scale use.DAC-Loop: Distillation-Aware Compression for Remote Sensing CNN
While large-scale models achieve strong results in remote sensing scene classification, deploying them on edge devices remains difficult due to limited compute, memory, and energy budgets.LEAP: a Latent Embedding Anomaly Patch-Transformer for time-series anomaly detection
Time-series anomaly detection is dominated by reconstruction-based neural detectors, whose objective is structurally flawed.Global $\mathcal{O}\left(k^{-2}\right)$ Convergence of Multilevel Gradient-Regularized Newton Methods
We develop and analyze multilevel gradient-regularized Newton methods for unconstrained convex optimization with Lipschitz-continuous Hessians.OrthoRF: Exploring Orthogonality in Object-Centric Representations
Neural synchrony is hypothesized to help the brain organize visual scenes into structured multi-object representations.mdRNAcat: A Molecular Dynamics RNA Catalog of REST2 Conformational Ensembles
Learning molecular models of RNA requires simulation data that capture conformational variability and provide consistent physical training signals.Understanding Practical Optimization in Machine Learning
Modern machine learning relies on practical optimization methods that often differ from the algorithms studied in classical analyses: they train submodels, clip or normalize gradients, use…Efficient Exact Unlearning for Federated Zeroth-Order Optimization
Federated zeroth-order optimization (FedZOO) reduces the memory and communication costs of collaborative training for edge intelligence by avoiding backpropagation while communicating only random…One-Shot Federated Model Editing for Device Dynamics at the Edge
Standard federated learning (FL) requires persistent device connectivity across multiple communication rounds, making it unsuitable for dynamic environments such as vehicular networks, where devices…SkillLifeBench: Benchmarking Security Across the Lifecycle of Agent Skills
Web agents reuse skills whose stored code, selected version, and loaded implementation can diverge across tasks and updates.Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment
Reasoning-tuned and reward-trained models are often assumed to verify more reliably because they reason longer or receive correctness signals.Beyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in Artworks
Emotion recognition in artworks remains challenging because affective meaning is often subjective, implicit, and shaped by relationships between visual form and semantic associations.NOMAD-EEG: Native Omni-Montage Adaptive Diffusion
Electroencephalography (EEG) montages, channel counts and recording lengths vary widely, but most EEG foundation models are bound to the channel set and input length they were trained on.Conversational Generalized Linear Bandits with Hybrid Feedback
Conversational bandits improve recommendations by actively querying users about key-terms to elicit their item preferences.