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 249
Intrinsic Geometry Matching: learning observation-equivariant process geometry
Real data are often arbitrary, indirect observations of an unknown underlying process, and those observations can distort its geometry.A physics-coupled graph neural operator for mid-plane six-component stress tensor field prediction in concrete penetration
The penetration-resistant design of concrete structures requires the spatiotemporal evolution of the stress field within the target, whereas in design only the strength grade, the geometry and the…Multi-Agent Deferred-Decision Trajectory Optimization with Anytime-Valid Target Retention for Moving Candidates
We study multi-agent terminal interception when one of several moving candidates is the unknown target and both target identity and candidate terminal locations are uncertain.Mixture of GFlowNets
Generative Flow Networks (GFlowNets) learn a policy that samples compositional objects in proportion to an unnormalized reward $R(x)$.MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation
Functional brain connectome represents neural connectivity as a matrix of pairwise interactions between brain regions.ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty
Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional class probabilities unknown.LLM Evaluation is a Forecasting Problem
Standard procedure in machine learning is to randomly split train and test data, emulating IID draws from one underlying data distribution.Understanding Personalization Gains in Whisper
Whisper-style ASR models provide strong zero-shot transcription, but their residual errors are not evenly distributed across datasets, recording conditions, and metadata-based groups.SPLICE: Sparse Physics Library Identification and Compositional Expansion
Neural operator splitting composes a library of neural operators, one per physical mechanism, into zero-shot simulators of new equations.Honeycomb Crystal in a Mass-Asymmetric Electron-Hole Bilayer
A two-dimensional electron gas in a uniform neutralizing background forms a triangular Wigner crystal at low density.MENTOR: Procedural Shielding of Tool-Using LLM Agents
Tool-using LLM agents are increasingly used to automate workflows governed by procedural manuals, such as company rules for booking travel or procuring hardware.Measuring Variable Importance Using Proportional Inclusive Marginal Effects
Shapley-based measures are widely used for measuring variable importance in statistics and machine learning.In-context classification: Calibration and noise in linear attention with softmax readout
We study in-context binary classification in a simple attention model trained to minimise a logistic loss.Gradient Routing Localizes and Removes Unintended Behaviors in RL
We propose a mitigation to reward hacking in reinforcement learning.TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings
Real-world tables are often heterogeneous, combining numerical features with free-form string columns.Nearest Neighbor Functional Curve Completion for Intraday Probabilistic Revisions of Renewable Generation Forecasts
We propose a nonparametric approach that fuses deterministic initial forecasts and a partial realization into a probabilistic forecast using the framework of functional curve completion.Towards Universal Calibration for In-Context Classification
In-Context Learning (ICL) has received a lot of interest recently due to its ability to improve classification accuracy for new tasks without having to fine-tune the model over these tasks.LocalTrain: Integer-Only Local Learning for Energy-Efficient CNN Training on Edge FPGAs
Local learning reduces cross-layer training dependencies, but an efficient accelerator must still retain operands, accumulate gradients, and select quantization scales.Masked Diffusion for Travel Diaries Synthesis
Because household travel surveys combine household characteristics, variable-length person rosters, vehicle rosters, and trip chains, existing synthesis pipelines split them across separate models…Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations
Existing interpretability tools do not test whether a representation keeps the same content when only the phrasing changes.