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 196
Latent State Utilization in Probabilistic Circuits
Probabilistic circuits (PCs) are generative models that support efficient probabilistic inference.Morpheus-2.0: Multiscale Probabilistic Forecasting with Dual-Axis Attention
A universal forecaster is trained once and applied everywhere, so it must serve tasks whose schemas, forecast horizons, and temporal resolutions all differ.PAC Learning with Query Feedback
We study realizable multiclass PAC learning with query feedback, where each training example provides a single binary response indicating whether its true label belongs to a chosen subset from a…IRAH: Hierarchical Agentic Tree Search for Retrieval Pipeline Optimization
Optimizing Information Retrieval (IR) pipelines for Retrieval-Augmented Generation (RAG) requires jointly selecting structural components and numerical hyperparameters under limited evaluation…Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy
We propose a general framework for non-interactive locally differentially private (LDP) learning of structured univariate distributions that can be approximated by piece-wise polynomials.INCONVENIENT: A Benchmark to Assess LLM Generalization Capabilities from Convenience Samples
Machine learning models for tabular prediction typically assume that training data are representative of the population on which they will be deployed.PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews
Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate what a paper says.SHIP: Structured and Hierarchical Insight with Privacy
Extracting insights from textual data while protecting user privacy is increasingly important.SALTO: Solver-Anchored Lifted Transfer Operators for Nonlinear Event Inference
Learned dynamical models can accurately predict trajectories while producing unreliable sensitivities when differentiated or transposed, limiting their use in inverse problems and scientific…Athanor: An Agent-Native System for Autonomous Post-Training Research
Recursive self-improvement, in which AI systems build stronger AI systems, is one promising route to superintelligence.Bellman-Consistent Trajectory RL for LLM Arithmetic Reasoning
To address sparse terminal rewards in LLM arithmetic reasoning, we propose a Bellman-consistent trajectory RL method.Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion
Discrete diffusion models have become a powerful framework for modeling complex discrete distributions across a range of applications.Adaptive Randomized Neural Networks for PDEs: Structure-Aware Feature Redistribution and Residual-Driven Block Enrichment
Randomized neural networks retain an output-linear least-squares solve, but globally sampled random features may fail to capture the spatial and scale structure of PDE solutions.StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction
Score-based diffusion methods usually perturb data with Brownian Gaussian noise, corresponding to a light-tailed forward stochastic differential equation (SDE).SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning
We identify a theoretical incompatibility between 3D point cloud masked autoencoding and SE(3)-equivariant networks.Probe-and-Resume: When and How to Evaluate Agent Execution
Test-time search can improve agent performance by exploring alternative actions and using a critic to select promising branches.ToolBottleneckBench: Measuring Tool-Agent Performance under Controlled Pressures and Fixed Harness Budgets
The success score of a tool agent reflects both its model and the budgets of the harness that runs it.Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows
When humans collaborate with AI agents on long-horizon tasks, what happens to the agents' contributions?Spectral-Spatial Interpretation
Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores.DST-Net: Decomposed Spatio-Temporal Network for Time Series Forecasting
Series decomposition has emerged as a widely acknowledged paradigm in deep time series forecasting models.