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 35
When Is Tracking Affordable? A Movement-Budget Feasibility Threshold for Dynamic Regret
Dynamic regret measures an online learner against a moving comparator, and standard analyses assume the learner may move freely at every round.In-context learning of solution to simple linear regression task using transformer with masked linear self-attention
In-context learning is a remarkable property of transformers and has recently received a lot of interest.Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion
Autoregressive video diffusion models (AR-VDMs) enable real-time, long-horizon video generation but degrade rapidly once the inference horizon outruns the training horizon, due to compounding…Efficient Detailed Scheduling of Multiproduct Pipelines using Action-Decoupled Deep Reinforcement Learning
Multiproduct pipelines transport refined products to delivery stations in sequential batches, and their detailed scheduling must meet market demand while respecting nonlinear hydraulic constraints.GraTED: Graph--Tensor EEG Decoding for Passenger Hazard Perception in Autonomous Vehicles
Passenger electroencephalography (EEG) can reveal road risk through anticipatory responses before hazardous events and neural reactions around their onset.Reimagining computational quantum research with AI scientists
AI scientists are expanding automated research across scientific domains, yet their ability to turn the scientific record into a foundation for autonomous discovery remains elusive.Iterated Narrow Networks: Turing Completeness at Width 4 on Convex Input Spaces and the Complexity of Verification
We study the iterates of a fixed ReLU network $N$ of width 4, that is, the discrete-time system $x_{k+1} = N(x_k)$ on $[0,1]^4$.NIR: Approximate Neural Instance Retrieval for ALCIQ
Instance retrieval is the main bottleneck of concept-learning systems based on refinement operators.Kolmogorov-Arnold Networks vs. Multi-Layer Perceptrons: A Rigorous Statistical Benchmark on Clinical Tabular Data
Kolmogorov-Arnold Networks (KANs) have recently been proposed as a promising alternative to Multi-Layer Perceptrons (MLPs).TensorLOB: Structure-Preserving Tensor Learning for Limit Order Book Forecasting
The limit order book (LOB) records outstanding buy and sell orders across multiple price levels.AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games
In this paper, we consider mixed-motive games (MMGs) which model various real-world multi-agent scenarios where self-interested agents must both cooperate and compete.Identifiable Signed Causal Learning via Latent Stochastic Differential Equations for Inferring Brain Dynamic Effective Connectivity
Understanding how brain regions interact to support cognitive tasks requires characterizing directed causal influences among them, known as effective connectivity (EC).Extending Aircraft Coverage of the Poll Schumann Model Using Public Data
The Poll Schumann model requires airframe and engine parameters, but published tables cover only part of the fleet.A Universal Policy Wrapper With Guarantees
Many control tasks require driving the system into a prescribed goal set and subsequently keeping it there.Gibbs Variational Last Layers for Long-Horizon Dynamics Learning
Accurate long-horizon probabilistic predictions of dynamical systems are a prerequisite for model-based decision-making.Zero-shot time-series foundation models against the Khepri v1.5 baselines for 96-hour carbon-intensity forecasts in nine Nordic bidding zones: a preregistered comparison
We compare three zero-shot time-series foundation models (Timestral-5M, Timestral-209M and Chronos-2, 8192-hour context, no covariates) with the Khepri v1.5 SARIMA and GBM baselines, with their code…Control Foundation Models across Changing Block Diagrams: Generalizing Time-Series Prediction to Dynamic Graphs
In the prediction and control of physical systems, combining records from different experiments and operations is expected to supply information that no single experiment provides on its own.Unimodal Augmentation-based SSL Objectives Induce Cross-Modal Alignment
Recent works have observed implicit cross-modal alignment between independently trained unimodal models.Unlocking the Potential of Contrastive Regularization for Diffusion Transformer Training
Representation regularization has emerged as an effective way to improve diffusion transformer training.ILR-SMO: Iterative Latent Refinement for Robust Spatial Multi-Omics Integration
Spatial multi-omics technologies jointly profile diverse molecular modalities with spatial context, providing a comprehensive view of cellular heterogeneity and tissue organization.