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 145
Tractable Inference with Kolmogorov-Arnold Networks
Machine-learning surrogates in computational science often require not only accurate predictions but also expectations, variances, conserved integrals, and normalization constants.Preventing Model Extraction in Contextual Linear Optimization
Consider a contextual linear optimization problem, where a predict-then-optimize (PTO) system returns optimal decisions without revealing the cost vectors used in its downstream linear program.Unintended Side Effects of Value Training in LLMs
As LLMs are increasingly deployed in value-sensitive contexts, aligning them with human values has emerged as a post-training objective in NLP, aimed at instilling additional values and guiding…Privacy in Context Is Being Overlooked in the Age of General-Purpose LLMs
As large language models (LLMs) continue to grow in scope and capability, privacy concerns are on the rise.Your Benchmark Is an Empirical Measure Over Difficulty
A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty.FrontierCS 2: A Benchmark for Computer Science R&D
Can LLM agents make contributions to frontier computer science R&D?Mastering Model Fit: Applications of the InterModel Vigorish for Interpretable Machine Learning
Accuracy alone gives little information about which features or model components improve probabilistic fit, which outcomes benefit, or how fit changes during training.CORD: Conflict-Aware Optimization for Joint RL and Distillation in Agents
Joint reinforcement learning and self-distillation combines task rewards with dense teacher guidance for agent training, but their gradients can partly cancel.The Price of Current-Effect Inference in Nonstationary Multi-Armed Bandits
Adaptive experiments use bandit algorithms to favor interventions with higher expected rewards.TIDE: Tree-Induced Fine-Grained Diagnostic Evaluation from Model Behaviors
Benchmark performance is the dominant standard for comparing large language models (LLMs), typically summarized by a single aggregate score, such as accuracy, pass rate, or rubric score.SCDM: Scalable Causal Discovery in Nonlinear Temporal Systems with Meta-Learning
Causal discovery from nonlinear multivariate time series is challenging in high-dimensional systems, where the number of candidate directed relations grows quadratically with the number of variables.EPIC: Rethinking Trust Regions for Autoregressive LLM Policies via Exact-KL Prefix Importance-Ratio Clipping
Reinforcement learning (RL) based on PPO-style clipping has become an effective approach to improving the reasoning capabilities of large language models (LLMs).Mitigating Model Collapse through Dreaming Learning
Training generative models on synthetic data causes loss of diversity and a decrease in performance, a phenomenon known as model collapse.Agent Behavior Maps: Locating Agents by What They Would Do, Without Running Them
LLM agents with similar success rates can follow different action sequences.Code Comprehensor: Hierarchical Documentation and Cross-Modal Retrieval for Large Repositories
Understanding large, complex, and rapidly evolving code bases remains a core challenge for software engineering at scale, hindering onboarding, maintenance, refactoring, and impact analysis.ExGrad: Beyond Suppression - Explicit Clean-Gradient Subtraction in Adversarial Training
Adversarial training derives updates from surrogate losses, but source-loss descent does not directly characterize an update's effect on adversarial margins.HGM-Dual: Lineage-Aware Guided Agent Harness Optimization for Long-Horizon Planning
Harness optimization, which improves an agent's prompts, tools, and workflows, is an increasingly effective way to enhance agents built on frozen or closed-source LLMs.Looped Uniform Diffusion Language Models
Uniform diffusion language models (UDLMs) generate text by iteratively denoising sequences of ordinary vocabulary tokens, any of which may be corrupted and subsequently revised.Loopholing All the Way: Language Modeling with pure Self-Conditioning
Recent Diffusion Language Models (DLMs) use Self-Conditioning (SC), or Loopholing, to improve their performance.From Classifier Heads to Encoder Prototypes: Personalized Federated Learning with Head-Derived Clustering
Personalized federated learning must decide which clients should share representations.