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 14
Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs
Chain-of-Thought (CoT) reasoning substantially improves Large Language Models (LLMs), yet its out-of-distribution (OOD) generalization mechanism remains theoretically underexplored.Graph Foundation Models Can Become Effective Multivariate Time Series Anomaly Detectors
Multivariate time series anomaly detection (MTSAD) relies on modeling both temporal dynamics and inter-sensor dependencies to identify complex system faults.Within-Family EfficientNet Scaling under Fixed-Resolution Transfer Learning for Spectral-Domain Optical Coherence Tomography Retinal Disease Classification
Background/Objectives: CNNs perform well in retinal disease classification from spectral-domain optical coherence tomography (SD-OCT), but whether EfficientNet's natural-image scaling hierarchy…How many sorted projections determine n points in k dimensions?
Let $d_1,\dots,d_m$ be directions in $\mathbb{R}^k$, where $k\ge 2$.The Alignment Tax Is Graded: Task-Selective Capability Loss Under Length-Normalized DPO with SFT Retention
Setting.What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?
While multi-turn agentic reinforcement learning (RL) excels on long-horizon tasks, its performance gains remain highly sensitive to interaction constraints.Model Merging Does Not Require Uniform LoRA Ranks
Model merging combines separately fine-tuned experts into a single model without retraining.Risk-Sensitive Non-Parametric and Kernel Bandits
We study non-parametric bandits in which arms are evaluated using Cumulative Prospect Theory (CPT) rather than expected reward.Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation
Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors.NaijaFacts: A Framework for Disentangling Language from Knowledge in Facts about Nigeria
Multilingual benchmarks for African languages mostly translate generic questions into local languages, measuring linguistic competence but not whether models know facts about Africa.ElecLoad: Adaptive Electricity Load Forecasting Guided by Multiple Events
Accurate electricity load forecasting provides critical decision support for energy procurement, generation scheduling, and supply-demand balancing, contributing to the economic efficiency and…Nowcasting Future Performance for Population Pruning in Survival-of-the-Fittest Training
Training high-performing neural networks often involves evaluating populations of candidate models with varying hyperparameters, architectures, or random seeds.An Interaction-Aware Decision Framework for FDIC-Assisted Distressed Bank Acquisitions: Empirical Evidence from the FDIC Failed-Bank Panel and the SVB-First Citizens Case
Acquirers of failed banks weigh acquisition value, regulatory protection, risk, buyer strength, and execution difficulty jointly, because each signal's meaning depends on the others: high…IDSISA: Influence-Distilled Sharded Training for Efficient Machine Unlearning
Machine unlearning removes the influence of specific training examples to comply with privacy regulations.EvoOPD: Evolving Privileged Information Strategies for Black-Box On-Policy Distillation
Proprietary language models exhibit strong reasoning and coding capabilities, but their output distributions are inaccessible, making fine-grained distillation methods that rely on teacher logits…Adapting Sleep Foundation Models for Dense Sleep Spindle Localization
Adapting sleep foundation models to dense electroencephalography (EEG) event localization is challenging because multi-second representations may not preserve sufficient temporal detail for precise…RAGAM-AI: A Hybrid Reinforcement Learning based Agentic approach powered by Generative AI for Edge Resource Management
Resource management for distributed edge networks hosting different services has been handled efficiently using Reinforcement learning (RL).From Fixed Defaults to Calibrated Activation Policies for Long-Term Time-Series Forecasting
Long-term time-series forecasting supports decisions in energy, transportation, and other applications where reliable predictions are needed beyond the observed data.Finite-width shift of the edge of chaos in deep neural networks
Deep neural networks train best when they are initialised at the edge of chaos, the critical line in the plane of weight and bias variances on which the distance between two inputs neither grows nor…Thermodynamics-Informed Learning Captures Hierarchical Hydrogen-Bond Networks in Deep Eutectic Solvents
Deep eutectic solvents (DESs) offer a tunable platform for lignocellulose refining, but their solvation behavior depends on multicomponent hydrogen-bond networks rather than individual constituent…