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 59
Unsatz: Evaluating Scientific Discovery Without a Given Ansatz
Before a scientist fits any parameter, they must decide what the model contains: which quantities exist, which are hidden, how they interact, and how they are measured.MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation
Self-distillation methods for large language models with an exponential moving average (EMA) teacher already retain a history of student updates.Differential rank preservation manifold learning
Manifold learning methods like t-SNE and UMAP preserve local neighborhoods, but they do not preserve the ranking of the neighbors inside them.TalentRL: Strategy-Guided Reinforcement Learning for Hierarchical Skill Routing
Natural-language skills enable large language model (LLM) agents to reuse procedures across tasks, yet most systems retrieve individual skills from a flat SkillBank without explicitly modeling the…Adaptive Uncertainty Quantification on Simplicial Complexes with Conformalized Simplicial Neural Networks
Simplicial neural networks (SNNs) are powerful tools for prediction tasks on higher-order relational datasets stored on simplicial complexes (SCs), a higher-order generalization of graphs.CAP: Learning to Optimize from Sparse Observations of Related Tasks
In experiment-driven black-box optimization, each evaluation can consume materials, equipment time, and other resources, limiting the number of experiments available for a new task.General Frequency Principle for Linear Approximation Classes
In this paper, we study a general frequency principle under gradient descent training for the finite linear approximation classes.Mechanistic Interpretability for End-to-End Self-Driving
End-to-end (E2E) autonomous driving models achieve strong planning performance but remain largely opaque, limiting observability and trust.When AI Investigators Cannot Trust Their Tools: Conflict-Aware Evidence Verification for Cyber Threat Investigation
LLM agents increasingly triage security alerts by combining the outputs of several detection tools, implicitly treating those tools as trustworthy.Role-Aware Server Optimization for Multimodal Federated Learning with Missing Modalities
Multimodal federated learning (MFL) trains a shared model by aggregating client updates without exchanging raw data.Shifting Focus by Reliability: Geometric Fusion Modulation for Robust RGB-T Detection
RGB-thermal (RGB-T) object detectors combine visible and thermal imagery for robust detection, but signal corruption in either stream can substantially degrade accuracy.Beyond Scarcity: When Encoder Adaptation Is Worthwhile
Long-tailed recognition often learns a shared representation before correcting the classifier for class imbalance.A Positional Realizability Theory of Length Generalization in Single-Head Attention
Why does length generalization (LG) depend so sharply on the positional encoding (PE)?Corroborative Learning: Mutual Enhancement through Task-Response Reconstruction
In pattern analysis, models trained independently for the same task often develop complementary capabilities through differences in architecture, data, and optimization.Generative SDEs with Trainable Diffusion and Density-Based Losses
We develop a divergence-kernel method for jointly optimizing neural SDE drift and diffusion fields and the initial Gaussian distribution, using losses that depend directly on the terminal density.A Unified Framework for Probability Estimation of Data-Dependent Events
We study the general problem of estimating $D(\dde(S))$, the probability that an unknown distribution $D$ assigns to an event determined by a sample $S$ of $n$ i.i.d.\ draws from $D$ through a known…Coarse-Graining Optimal Transport for Rollout-Free Post-Training of Flow Matching
Flow matching depends critically on the coupling used to pair source and target samples.SPT-Flow: One Integration, Many Futures in Continuous-Time World Models
Continuous-time world models generate a latent trajectory through a single ODE integration, but adding stochastic conditioning does not ensure that the model uses it.AuditFL: A Contract-Backed Clearing Layer for Open Federated Learning
Federated learning (FL) keeps raw data local, but most deployments still rely on a trusted coordinator for client admission, checkpoint distribution, update collection, aggregation, and rewards.Estimation of Quantum Umlaut Information
Quantifying correlations is important for understanding how quantum states and channels support information processing.