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 126
A Measure-Geometric Theory of Robustness in Machine Learning
This paper develops a foundational measure-geometric theory of robustness in machine learning.Inference-Time Prior Adaptation for Imbalanced Data Streams under Concept Drift
Data stream classification under concept drift and class imbalance requires models to adapt continuously while maintaining strong minority-class performance.Speculative Forking: Turning Idle Wait into Parallel Exploration for Repository Environment Setup
Before developers can use a software project, they must first get it to run.Ampe-DB: A Dataset for Human Activity and Interaction Analysis Using the Ghanaian Game Ampe
Human activity recognition benchmarks underrepresent culturally situated forms of movement and interaction.Physics Informed Neural Networks for Solving the Drift-Diffusion Equations
The drift-diffusion equations are the fundamental building block for the modeling, design, and optimization of modern semiconductor devices.Learning Pathology-Sensitive Representations for Unsupervised Retinal OCT Anomaly Detection
Deep learning approaches for retinal optical coherence tomography (OCT) predominantly rely on predefined disease categories, limiting their ability to detect rare or previously unseen abnormalities.Fully quantum training of parametric circuits with Quantum Hamiltonian Descent
Parametric quantum circuits are usually trained by classical, local optimizers, which use the quantum computer only to evaluate the cost function, or its gradient, one point at a time.Neural-DISCO: Source-Conditioned Counterfactual Editing of Neural Population Activity
Understanding how neural activity encodes behavioral and sensory variables is a key challenge in systems neuroscience.Modeling Liquid-Cooled Data Centers in EnergyPlus
As AI workloads accelerate data center transition toward high-density racks with direct-to-chip (DTC) liquid cooling, existing simulation tools remain limited in evaluating whole-building and…How Much Fresh Data Should CTR Recalibration Use? A Temporal Evaluation of Post-hoc Calibration
Offline evaluation of click-through rate (CTR) models still defaults to random splits, although deployed models score future traffic and downstream systems consume calibrated probabilities.Learning the Past from the Future: Retrospective Reconstruction in Temporal Interaction Networks
Temporal link prediction uses past interactions to predict future links.A Gaussian Process State Space Formulation for Materials Constitutive Modeling: Application to Quasi-brittle Materials
Constitutive models for history-dependent, path-dependent materials typically encode this dependence in prescribed functional forms through internal variables such as damage or plastic strain that…Kernelised covariance matrices, dimension reduction and imbalanced spectral clustering
The Gaussian Mixture Model (abbrv.Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning
Alignment evaluations aim to assess whether large language models would engage in dangerous misaligned behaviour.Support-guided OOD Removal with Diffusion
Many real-world signals are corrupted by localized, structured perturbations whose distribution is unknown: an intermittent background noise in a music recording, a watermark stamped on a…Flow Mesh: A Velocity-Regularized Flow Matching Framework for Stable Distributional Modeling of Physical Fields on Unstructured Meshes
Thermal-fluid field distributions underpin the analysis and operation of energy infrastructure, from nuclear-reactor cooling channels to industrial heat exchangers, but resolving these distributions…Lower expected Fisher rank implies better PAC generalization
Deep learning architectures tend to generalize well to unseen data, but explaining this capability is still an open area of research.Model-agnostic predictability quantification of multivariable time series
Multivariable time series forecasting plays an important role in various domains, where predictions depend on complex interactions among covariates.Vision Token Pruning via Query-Vision Interaction Decomposition
Large vision-language models (VLMs), which process both visual inputs and text queries, incur high inference costs due to the large number of visual tokens, making visual token pruning a natural…Neyman Orthogonal Activation Steering
Activation steering is a popular approach for shifting LLM output toward a desired behavior, and increasingly for generating realistic synthetic data.