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 12
Short-Term Forecasting of Heterogeneous Wind Power Fleets: Global Temporal Fusion Transformer Leveraging Static Covariates
Accurate short-term wind power forecasting is critical for grid stability and electricity trading.SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving
Mixture-of-Experts (MoE) language models send each token through a few of many expert subnetworks.CARM: Conformal Adaptive Risk Masking for Reliable Scientific Super-Resolution
Deep learning-based super-resolution (SR) can reconstruct fine-scale Earth-observation fields from coarse observations, but reconstruction accuracy alone does not provide a calibrated rule for…Neural Stochastic Forecasting for Lateral Molecular Diffusion Simulations
Predicting the long-time diffusion of membrane proteins is challenging because molecular dynamics (MD) simulations are computationally expensive, while experimental single-particle tracking is often…Selective Prediction Intervals: Jointly Learning to Predict, Bound, and Abstain
Many high-stakes regression decisions ask three things of a model at once: a point estimate to act on, an interval that bounds the risk of acting, and the option to abstain when neither can be…Regret Bounds for Market Making with Persistent Orders
We study adversarial market making with orders that remain active until execution.FaCoDiff: Factor-Correlated Diffusion for Multivariate Probabilistic Forecasting
Multivariate probabilistic forecasting requires modeling cross-variable dependence alongside marginal uncertainty.AssameseLM-E2B: An Open-Weight Assamese Language Model for Efficient Consumer-Grade Deployment
While Large Language Models (LLMs) excel in high-resource languages, their performance often degrades in low-resource languages due to tokenization inefficiencies, generative instability, and…Network Intrusion Forensic Detection System with Explainable Artificial Intelligence and Digital Chain of Custody
Deploying an explainable intrusion detection model from a validated laboratory setting into a forensic workflow requires guarantees that benchmarks do not test: that the certified model is the exact…Chiron: Cache Management Empowered by LLM Intelligence for AI Workloads
AI clusters keep data in remote object stores and rely on local caches to stop GPUs from waiting for data.GPUMAP: GPU-Accelerated Progressive Uniform Manifold Approximation and Projection
Dimensionality reduction (DR) techniques are fundamental to the analysis of high-dimensional data, yet their substantial computational cost limits their use in interactive settings.Cross-Asset Knowledge Transfer for Early Fault Detection of Data-Scarce Assets Without Target Fault Data
Reliability management of industrial fleets depends on early fault warnings, yet lifecycle data across similar assets are highly imbalanced.Loop Before You Leap: What Recurrent Depth Can and Cannot Buy in Data-Limited Pretraining
Multimodal models have often scored below text-only baselines in the BabyLM Challenge (Klerings et al., 2024; Takmaz et al., 2025).A Definition of Catastrophic Performance
A central challenge in AI is specifying objectives that align with human preferences.Consistent Submodular Maximization with Full Foresight
Online algorithms with bounded recourse face three intertwined obstacles: uncertainty about the future, computational limits, and a limited budget for changes.Separation Is a Riesz Energy: How Many Environments Does ICA Need?
Can independent components be recovered when all of them are Gaussian?Zuse: A Decision Model for European Languages
Decision models read a document and return a probability for each of a fixed set of options instead of generating text.Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
Reinforcement learning with verifiable rewards (RLVR) has led to significant gains in math and code generation.Learning Noise Optimization for Reward Alignment in Few-Step Generative Models
Reward alignment for diffusion- and flow-based generative models is often formulated over stochastic trajectories, making it less suitable for few-step deterministic generators.Analysis of Local Open-Weight LLM Agents on Vulnerability-Reproduction Tasks
Open-weight language models that fit on a single consumer GPU are becoming capable on a growing range of tasks, and they matter because they can run locally without sending the code to a hosted…