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 115
A Unified Analysis of Importance-Corrected Momentum Actor-Critic over a Markovian Trajectory
We present a generic actor-critic method that combines a ridge-regularized pathwise least-squares temporal-difference (LSTD) critic with importance-corrected momentum (ICM) actors.Energy Efficient Lung Tumor Segmentation with a modified CBAM ENet Skip Model
Lung tumor segmentation plays a vital role in early detection and treatment planning of lung cancer.Climate downscaling with likelihood functional flow matching
Decisions about heat, frost and flooding are made locally, yet reanalyses and climate models resolve tens of kilometres.Error-Subspace Calibration for Multi-Task Model Merging
Model merging combines task-specific expert models into a single model without joint training on their original datasets, but often incurs a performance gap relative to the individual experts.Explicit Frictional Contact Modeling in Neural Garment Simulation
Graph neural networks (GNNs) simulate garments efficiently through physics-based self-supervision, but leave body-garment friction implicit or inside training energies, with no friction coefficient…RBGA: Residual-Budget Guide Arbitration for Offline-to-Online Safe Reinforcement Learning in Dexterous Manipulation
Dexterous manipulation requires robots to leverage existing datasets for rapid skill acquisition while maintaining safety during real-world deployment to prevent damage to the robot or its…FedSEAM: Federated Continual Learning of LLMs via Subspace Expert Agreement Merging
Federated continual learning trains a model on a sequence of tasks across several clients without sharing their data while retaining knowledge of earlier tasks.DualPace: Decoupled Scheduling and Cooperative GPU--CPU Decoding for LLM Serving
Large language model (LLM) serving relies on batching to improve inference throughput, but the key-value (KV) cache grows with sequence length and limits GPU-resident concurrency.Towards a Learnable Retriever for Textual Graph Question Answering
Textual graph question answering (GraphQA) and graph-based retrieval-augmented generation (GraphRAG) have gained increasing attention as a way to ground large language models (LLMs) on structured…Overlap-Aware Sub-hypergraph Pattern Frequencies for Hypergraph-Level Classification
Classifying whole hypergraphs requires a fixed-length description of inputs whose numbers of vertices and hyperedges vary.Collective Collaboration of Recursive Autonomous Agents
Smart factories must translate order-level objectives into production tasks at multiple scales and combine the capabilities of individual units into an overall delivery capability.Affine-invariant Cubic Newton with Weak Learners
Modern gradient boosting algorithms are based on Newton's method, which excels empirically but lacks global convergence guarantees.Optimizing Physical Neural Networks through Device Variable Selection
Physical neural networks (PNNs) leverage device physics in electronics, optics, and related domains to enable energy-efficient neural networks.Implicit Beliefs as Scalable Process Rewards for Strategic Persuasion
Training large language models (LLMs) for multi-turn strategic persuasion faces two coupled obstacles: (i) realistic simulation of psychologically grounded persuadees, and (ii) dense, faithful…Clustering of High-Dimensional Human Gene Score Data for Target Cell Classification
The goal is to investigate whether the total human gene-score dataset and the selected human kinase-gene dataset exhibit the same number of clusters when analysed using the same set of 769 features.Patch-Derived or Register Tokens? Comparing Variable-Length Image Tokenizers
Image tokenizers convert pixels into compact latent sequences for efficient generative modeling.Nowcasting aerosol particle size distributions from PM2.5 with physics-regularized flow matching
The mass concentration of particles smaller than 2.5um (PM2.5) is cheap to measure and widely monitored, whereas the particle number size distribution (PSD) requires costly instruments and is…Joint End-to-End Training of Weighted BP Decoder Ensembles
Ensemble decoding improves decoding reliability by combining component decoders with complementary failure events.Variational Atlas Autoencoders and Self-Supervised Chart Selection
Complex, high-dimensional data lie on manifolds that a single global latent coordinate system cannot represent without distortion.Counterfactual Model Testing Under Distribution Shift
Deployed machine learning (ML) models can degrade as the distribution of their input data shifts.