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 174
LowNet: Looped Wavelet Neural Networks with 24 Learnable Parameters for Solving Poisson Equations
Poisson equations frequently appear in various fields, such as mathematics, physics and informatics.Robust Direct Preference Optimization under Preference Label-Flip Attacks
Direct Preference Optimization (DPO) is widely used for offline Reinforcement Learning from Human Feedback.Over-Defense in Coding Agents Begins at Silent Forks
Language models behind coding agents are post-trained with outcome rewards, and recent methods concentrate credit on the turns that decide the outcome.ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
Next-token prediction leaves hidden-state trajectories largely unconstrained, while existing geometric regularizers primarily control the direction rather than the magnitude of trajectory deviations.CasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning
Reinforcement learning (RL) is a promising way to improve the clinical reasoning abilities of large language models (LLMs), but current pipelines often rely on expert-labeled questions or costly…Revealing what benchmark scores hide: Jointly measuring the breadth and reliability of LLM capabilities using accessibility profiles
Language model benchmarks assign each question a single outcome from one fixed wording, even though the same underlying request can be expressed in many equivalent ways.Label-Space Mismatch Distorts Cross-Cohort Evaluation in Breast Cancer Molecular Subtyping
Cross-cohort evaluation of breast cancer subtype classifiers is unreliable when source and target cohorts use different annotation standards: METABRIC labels six classes, PAM50 defines five, and a…PRECOCIAL: Pretraining with Code Curriculums via Iterative Search for Accelerated Learning
Fully synthetic pretraining data generated by symbolic programs can bootstrap downstream training on naturalistic tasks, such as language modeling, but the generating programs have so far been…Certified Sparse Attention via Perturbed Retrieval
Sparse attention speeds up long-context decoding by reading few keys of the KV cache, but existing methods do not control the error of a query, and on real KV caches their errors have heavy tails.Block Recursive Transformers for Structured Parameter Sharing
Recursive Transformers depend not only on how many parameters are shared, but also on how shared parameters are organized across depth.SoK: PIAtlas: Decomposing the Unbounded Prompt Injection Attack Space
Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field still lacks a coherent map of how these attacks are constructed.UtoMe: Observation-Uncertainty-Guided Token Merging for Weather Foundation Models
Weather transformers process dense reanalysis fields whose reliability varies across variables, locations, and weather regimes.UpLoop: Upcycling Large Language Models with Gated Loop
Looped large language models trade parameter storage for recurrent computation, but most are trained from scratch.No Escape from the Quadratic Barrier: Adaptive Attacks on Linear $\ell_2$ Sketches
Linear sketches estimate properties of high-dimensional inputs from a fixed low-dimensional projection.Conjugate Compilation: Self-Improving Agentic Co-Compilation for Speculative Decoding
As LLM adoption surges, scaling model serving requires unlocking stranded GPU capacity alongside deploying more GPUs.Latent World Models Should Plan with Distances Along the Latent Manifold
Latent world models such as LeWM plan by searching for an action sequence whose predicted terminal latent is closest to the goal latent under an ambient norm, such as the Euclidean distance.Multifidelity Monte Carlo Estimator for High-Dimensional Quantities of Interest
Multifidelity Monte Carlo (MFMC) reduces the cost of estimating the statistics of quantities of interest (QoIs) computed via expensive high-fidelity model by using cheaper low-fidelity models as…Decentralized Online Exp-Concave Optimization
Decentralized Online Convex Optimization (D-OCO) is a fundamental framework in which a set of local agents aims to minimize a sequence of global loss functions using only local computations and…LLM Agents as Suppliers of Physical System Models: Calibration and Acceptance in Modelica
To procure a model of a device, a client hands a supplier a description, sometimes with recorded data or a target response, and accepts the model against this handover.Synergy-Aware Residual Flow Matching for Single-Cell Perturbation Prediction
Predicting single-cell responses to genetic and chemical perturbations is important for understanding regulatory mechanisms and prioritizing therapeutic interventions.