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 149
Collaborative In-Context Learning for Indoor Radio Map Estimation
Indoor radio map estimation (RME) is essential for wireless applications such as coverage planning, localization, and network deployment.The Path to NDE 4.0: A Review of Algorithms, Techniques, and Strategies for Autonomous Inspection
Non-Destructive Inspection (NDI) is a cornerstone of modern quality assurance, critical for ensuring the safety and reliability of infrastructure and manufactured components without causing damage.Learning the Geometry of Materials Space with Trained Neural Tangent Kernels
Neural networks trained to predict materials properties learn representations whose physical content can be difficult to extract.The Router Already Knows
Mixture-of-experts (MoE) models already make a sparse choice for every token: which experts should process it.Baseline and Incremental: User, Item, and Request Debiasing in Instagram Feed Ranking
A feed ranker scores candidates with a value model, a weighted sum of engagement predictions.MLIPS: Multi-Layer Indexer Pool Sharing
Sparse attention limits the keys used by each query, but finding those keys can still require a full-prefix scan at every layer.Scaling Graph Reasoning in Language Models with Learnable Graph Positional Encodings
Solving reasoning tasks supported on graphs typically requires providing a Language Reasoning Model (LRM) with a serialized description of the graph.Learning-Theoretic Foundation for General Coded Computing: The Adversarial Setting
Adversarial workers pose a severe challenge in distributed computing systems by returning corrupted outputs that can substantially distort the recovered computations.Using Set Learning to Improve Set-Valued Classifiers on Long-tailed Data
Set-valued classification (SVC) offers a practical approach to communicating uncertainty while maintaining accuracy by predicting variable-sized sets per input rather than fixed-sized sets (e.g…LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA Composition
Low-rank adaptation (LoRA) attaches small low-rank matrices to a frozen backbone, and public repositories host many LoRAs per backbone, each for a different concept or task.Decision Sufficiency of Learned Representation Interfaces for Safe Generative Control
A controller can guide a language model toward safe and useful responses by choosing when to assist, ask for clarification, or refuse.Beyond Scalar Leaderboards: Adaptive Sampling for Pareto Frontier Identification in Multi-Objective LLM Arenas
The evaluation of large language models (LLMs) is inherently multi-objective, as different models may offer different tradeoffs across performance dimensions such as math, code, and writing.Projected Distillation: On Learning to Solve Hard Problems from Close, Correct Targets
On-policy learning is central to post-training: training on a model's own generations limits distribution shift and helps preserve existing capabilities.Training-Free Continual Learning for Multimodal Forecasting via Prompt Evolution
Adapting a forecasting system to a changing world classically means retraining.Beyond the Prompt: Recovering Hidden Concepts in Text-to-Image Models
Text-to-image models can generate visual concepts that their prompts never mention, and recent work shows that such associations can be implanted so that ordinary prompts trigger them.When Parameter Gradient Flows Close in Representation Space
The represented gradient flow of a parameterized model depends on a mobility that can retain hidden parameter information.Orthogonal Boundary Unlearning for Dual-Use Concepts in Large Language Models
Mitigating catastrophic risks from large language models requires excising hazardous operational capabilities, such as cyberwarfare exploitation and pathogen enhancement, without degrading benign…MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning
Real-world audio typically contains concurrent sound events, yet standard self-supervised methods treat each clip as an isolated training unit without explicitly modeling mixture--constituent…Self-Evolving Agents through Privileged Retrospective Distillation
Self-evolving agents aim to improve from their own experience rather than remain fixed after deployment, but naturally collected trajectories often lack ground-truth solutions or verifier-derived…Soliton Profiles in 1D: Enhanced Neural-Network Solvers and Constrained Deep Ritz Methods
We develop and compare enhanced neural-network solvers for one-dimensional ground-state profiles, which are solutions of $$ Q^{\prime\prime}=bQ-γQ^{p},\quad Q>0,\quad p>1, \quad b, γ>0, $$ the…