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 31
Embedding a de Rham Complex Structure into Eig-PIELM for Maxwell Eigenvalue Problems
The perfect electric conductor (PEC) boundary condition alone does not eliminate the gradient nullspace of the Maxwell curl-curl operator.MemShift: Separating Detection from Repair in LLM-Derived Personal Memory
AI assistants store values that a language model derived from a person's records under the person's own definitions, such as their important contacts.On Stochastic Continuous-Time Linear System Identification for Adaptive Stabilization
Learning to stabilize an unknown continuous-time stochastic linear system is a central problem in control theory and reinforcement learning.Agent Memory as Rate-Limited Filtering: Explicit State Outlasts Long Context Beyond a Reader-Dependent Horizon
Can a language model that reads the full history of an access log say whether a service may act now?Prior Action Control Causally Alters Language-Model Plasticity
Two copies of one language model start from identical weights and receive the same rewards during training.Do Visual RL Gains Scale at Test Time? A Quantile View of Post-Training
Reinforcement learning (RL) post-training improves the single-sample quality of visual generative models, but deployment often provides additional inference compute through Best-of-N sampling.Nearest Is Not Safest: Fluid-Antenna Port Selection for Over-the-Air Backpropagation in Urban Multipath
Over-the-air backpropagation returns a loss gradient through the reciprocal channel, which requires the return port to see the channel of the forward port.EviCast: Forecasting Retrieval Gains Through Shared Response Calibration
Retrieval-augmented generation (RAG) extends large language models with external evidence, yet relevant evidence does not ensure that a generator can use it.Which Chains to Calibrate for Physical Backpropagation: Per-User Factors Versus Base-Station Chains
In physical backpropagation, users return loss derivatives over the time-division duplex uplink, giving the base station the downlink gradient without channel reconstruction.When Rewards Depend on the Group, GRPO Plays a Tournament
Rewards for diversity, coverage and distribution matching make the reward of each sampled response depend on the rest of its group, and they are now routinely optimized with GRPO and RLOO.Deployment-constrained key estimation with a DSP-guided transformer reranker
Local music applications estimate key during library import and benefit from an analyzer that is small, fast, and runs in-process.A Novel Federated Learning Framework for Defending Against Gradient Inversion Attacks
Federated Learning (FL) offers a paradigm for collaborative machine learning model training among clients, preserving data privacy by avoiding direct data sharing.A Scientific Claim Stability Framework for Evaluating MRI Morphometry Pipelines
MRI morphometry pipelines are often evaluated by measurement agreement or downstream accuracy, yet their scientific value depends on the conclusions they support.Behavior-Discriminative Reward Shaping for Reward-Robust Reinforcement Learning
Reward-robust RL typically models misspecification by specifying an uncertainty set that constrains the discrepancy of plausible rewards from a base reward.Architecture-Aware Mixed Precision for Replica-Exchange Training of Geometry-Aware Neural Operators with Uncertainty Quantification
Geometry-aware neural operators face substantial computational and memory demands when learning across complex physical domains.Singularity-Induced Local Complexity for High-Dimensional Learning Models
Many overparameterized models that have achieved remarkable success are singular models.A Parameter-Free Best-of-Both-Worlds Policy for Queueing Bandits
We study online channel scheduling for a single queue served by $K$ channels under bandit feedback.Diagnosing Model--Item Interactions in Language Model Benchmarks with LSIRM
Language models with similar benchmark accuracy can succeed on different items.M3Former: Fine-Grained Cross-Layer Mixing for Transformers
Residual connections give each Transformer block access to all earlier layers only through one fixed sum, broadcast to all of the block's inputs.Evaluating Synthetic Skin Lesion Images for Classifier Training: A Safety-Aware Algorithm
Skin cancer classifiers need large sets of annotated images, which are scarce, especially for rare lesion types.