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 208
HeRE: A Novel Benchmark for Hebrew Relation Extraction via LLM-Guided Denoising of Knowledge Graph Alignments
While LLMs demonstrate strong capabilities in English Relation Extraction (RE) tasks, a significant gap remains in assessing their RE performance in low-resource languages, due to a lack of…On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction
Diffusion language models (DLMs) promise parallel text generation, but in practice face an unresolved speed-quality trade-off.When Plans Change, Remember: Replanning-Guided Visual Memory for Vision-Language-Action Models
Long-horizon, multi-stage Vision-Language-Action (VLA) policies often require visual information that is no longer present in the current observation.Deterministic Bounds on Accuracy and Stability of Metric-Space Regression and Classification
Data-driven approaches often face ambiguity in datasets due to sensor or target noise, insufficient information, and noise in the input data.Coverage Cliffs in Off-Policy Quantile Certification
We study when logged contextual-bandit data can certify an upper tail quantile for a policy selected from the same sample.Structure-Aware Spatial Kernels for Gaussian Process Distributed Port-Hamiltonian Systems
Gaussian process distributed port-Hamiltonian systems (GP-dPHS) enable data-driven modeling of distributed dynamical systems while preserving their physical structure.Embodiment-Classifier Guidance: Transferring Frozen VLAs Across Robot Dynamics without Demonstrations
Flow-based policies such as $π_0$ are trained on a fixed set of embodiments, and transferring them to new ones is an open problem.Noise-Robust Forced Alignment for Spontaneous Speech
We show that forced aligners degrade on spontaneous, noisy real-world speech, and that fillers, laughter, and disfluencies corrupt word boundaries, impacting many downstream applications.Initiating Removal from Operational Symptoms in Federated Vehicular Networks
Connected vehicles train a driving model through federated learning (FL) and drive with it, so a faulty contribution often surfaces only as a delayed symptom on the road.Flat Loss, Evolving Features: Grokking in Modular Addition
Can a network keep learning while its training cross-entropy stays nearly flat at a positive level?Diagnosing GNN Failure Modes with Layer-Wise Probe Entropy
Graph neural networks (GNNs) are typically evaluated only at their final layer, obscuring how task-relevant information evolves during message passing.Can LLMs predict the outcomes of machine learning experiments?
Recent advances in AI make Recursive Self-Improvement (RSI) increasingly plausible.Rarity of Singletons Matters & Supplementary Materials
Estimating missing-mass and unseen-species counts from finite samples relies heavily on rare-event occupancy statistics, particularly singletons.Shift-Reliance Alignment: Ranking Vision-Language Models by the Cues They Trust
Vision-language models (VLMs) are usually chosen from leaderboards, which give one ranking for every application.Noise-shaped Sampling and Annealing for Scalable On-the-edge Training of Binary and Ternary AI Models
The training loss of binary and ternary neural networks, expanded as a multilinear polynomial over the discrete weights, is structurally equivalent to the energy of a hierarchical high-order Ising…Understanding Stability of Outer Nesterov Momentum on Stochastic Pseudo-Gradients
Large neural networks are commonly trained across many workers, and communication between them is a major cost.Network-Wide Freeway Speed Nowcasting and Forecasting from Sparse Fixed Sensors with a Probe-Supervised Graph Convolutional Recurrent Network
Traffic agencies need current and near-future speeds on every link of their network, but their fixed sensors cover only part of it.Alert-List Concordance for Evaluating Imputation Strategies in ICU Sepsis Prediction
Preprocessing is an under-measured reliability risk in clinical prediction: a model can keep a similar AUROC and still change who receives an alert.The Ephemeral Cost of Switching Optimizers Across LLM Training Stages
Recent work suggests that switching optimizers between pretraining and subsequent training stages incurs a performance cost, but systematic investigation of this phenomenon is lacking.Is a Linear Probe Evidence of a Linear Representation?
The linear representation hypothesis holds that pretrained vision models encode generative factors as linearly decodable directions in feature space, and comes with a standard methodology: train a…