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 37
Diagonal Equivalence in State Space Models: Characterization, Retrieval Rank, and Selective Extensions
We classify real and complex state-space models (SSMs) with linear transitions, distinguishing fixed-basis diagonal equivalence from input-output equivalence and tracking coefficient-conditioning…Preprocessing Choices in Fine-Tuning Data Matter: Utility and Demographic Sensitivity in LLM-Based Recommendation
Large language models (LLMs) have introduced a generative approach to recommendation, producing item lists from textual representations of user histories and item information.Inner optimizers in active-learning Kriging reliability analysis: a pre-specified comparison and the unconservative estimates left by unlearned failure modes
Active-learning Kriging often replaces candidate pools by continuous metaheuristic search.Controlling Sharpening in LLM Post-Training
LLM post-training via reinforcement learning has shown consistent improvements in accuracy at the cost of reducing behavioral coverage - a phenomenon known as sharpening that can stall progress on…FlowBatt: Flow Matching for Probabilistic Battery Degradation Prediction
Battery degradation remains a central challenge in the development and broad application of sustainable energy technologies.From PID to Reinforcement Learning in Building HVAC Control: A Control-Architecture Review of Tuning Strategies, Formulations, and Deployment Trade-offs
This paper reviews control architectures for building heating, ventilation and air-conditioning (HVAC) systems, addressing the tension among energy demand, occupant comfort and equipment…PaddleMaterials: An End-to-End Deep Learning Toolkit for Materials Science
Machine learning supports materials design, atomistic simulation and experimental characterization, yet models and workflows remain fragmented.Dissecting Geometric Constraints in Grokking: Interaction-Dependent Acceleration in Modular Arithmetic
Spherical transformer configurations can accelerate grokking through simultaneous modifications of several model properties.LaBraM at Scale: Scaling Data and Models for EEG Pretraining
LaBraM, an early EEG foundation model, demonstrated that large-scale EEG pretraining can yield strong representations for diverse downstream tasks.Causal discovery needs explicit epistemic standards
There are many causal discovery algorithms, but few guiding principles for choosing between them.ViAdminShift: A Vietnamese Benchmark for Event-Level Knowledge Updates Built from the 2025 Administrative Reform
On July 1, 2025, Vietnam reduced its 63 provinces to 34, abolished its 696 districts, and replaced its 10,035 commune-level units (wards) with 3,321.CISA: Retrofitting Dense Attention Models with Chunk-Indexed Sparse Attention
Long-context LLM inference is costly because attention repeatedly reads a growing key-value (KV) history.On the Convergence of Vanilla Adam under Heavy-Tailed Noise and Index Sampling
Understanding how stochastic gradient noise affects the convergence of Adam is an important problem in stochastic optimization, particularly when the noise exhibits heavy-tailed behavior.DynSL: Resource-Adaptive Model Training across Heterogeneous Edge Devices
Training models over data distributed across edge devices presents a trade-off: centralizing data simplifies training but raises privacy and regulatory concerns, while full local training may exceed…CFD-driven symbolic regression of RANS transition models
Laminar-turbulent transition governs skin friction, heat transfer and losses in turbomachinery, yet Reynolds-averaged Navier-Stokes (RANS) transition models rely on empirical correlations and…CERBO: Certified Recourse at a Requested Rate for Gradient-Boosted Trees
Recourse-aware learning trains models so that people who receive an adverse decision can reverse it with an affordable change.What Structurally Breaks an Agent? Auditing Difficulty in Stateful Tool-Use Workflows
An aggregate task score does not distinguish failures of scheduling, state retention, and candidate selection.Forecasting How RLHF Responds to Reward-Model Edits Before Training
Responses with headers, lists and greater length receive high scores from reward models (RMs), and RLHF policies learn to produce these features even when true quality does not improve.A Common Language for Dynamic Graphs: Interaction Tokenization Enables Foundation Models
Dynamic graphs capture evolving interactions in Web systems, including online communication, user engagement, and recommendation.Anomaly-ranked confirmation slows new-class learning
Anomaly detectors rank unfamiliar examples for expert confirmation, and the confirmed examples teach a classifier to recognise a new class.