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 239
Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization
With the growing number of LLMs available, selecting which one to use for a prompt has become a key question.Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings
While causal discovery methods have matured for complete data, such algorithms for handling missing values remain limited.Narrowing the Collaboration Gap, Probably
Large language models are increasingly deployed as teams of agents that hold different private information about a shared task.Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine
The Continuous Thought Machine (CTM) is a recurrent network that attends to inputs and makes predictions based on the synchronization between its neurons.Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion
Large language models impose substantial memory demands and arithmetic costs during inference.From Detection To Anticipation: Continuous Onset Forecasting For Stuttered Speech
Automatic stuttering systems primarily detect dysfluencies after they have occurred, limiting their use for anticipatory intervention.LLMs program using Reusable and Composable Abstract Representations
When writing code, the same computation can be expressed in different programming languages and through different implementation strategies.FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing
Financial disclosures express the underlying relationships of double-entry accounting through unstructured text.Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction
Equivariant structure-prediction pipelines alternate coordinate updates with the construction of a k-nearest-neighbour (kNN) graph whose membership is a discrete, piecewise-constant function of the…Multi-Sensitive Distributional Fairness: Joint Wasserstein Audits and Shapley Allocation
Fairness audits with several sensitive attributes are often performed one coordinate at a time.Beyond Time Induction: Structured Conditional Neural Solvers for Parametric Stochastic-Volatility Pricing
Physics-informed neural networks provide a flexible framework for learning parametric PDE solution families without labeled data, yet preserving accurate derivatives across heterogeneous regimes…Exploring Interpretability in Deep Learning-Based Forest Classification - Separating Similar Forest Classes using Sentinel-2 Time Series
The ecological insurance theory posits that diverse forests are more resilient and better able to adapt to changing environmental conditions.Outcome-Routed Distillation and Reinforcement Learning for Diffusion Language Models
On-policy distillation provides dense supervision on the student's own samples, but its targets still come from the teacher.Dimension-Free Scaling Laws for Size Generalization: An Exponential Separation
Modern machine learning models increasingly operate on variable-size structured data, such as sets and graphs.Exact Scaling Laws for a Random-Features Bigram Model
Understanding neural scaling laws is increasingly important for theory and practice, yet first-principles explanations remain limited even in simple settings.Verifier-Grounded Agentic RL for Provably Correct Code
Reinforcement learning for code usually rewards passing tests, which a model can do while remaining wrong on the inputs the tests do not cover.DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision
On-policy distillation (OPD) provides dense token-level supervision on student rollouts, but this supervision can become unreliable when the student and teacher diverge, either because of a large…Did the LLM Answer the Question? A Semantic Reconstruction Game for Jailbreak Evaluation
Jailbreak attacks against large language models (LLMs) are evaluated using attack success rate (ASR), which depends on correctly identifying responses that fulfill prohibited requests.Historical-Feature Residual Adaptation for Sequential Screening
Sequential screening policies must use acquired feedback effectively under a fixed experiment budget.Global-in-time Spectral Duhamel-Picard Method for Post-Exposure Bake Simulation and Physics-Informed Neural Operators for EUV Lithography
We present a global-in-time spectral Duhamel-Picard method with polynomial expansions for post-exposure bake (PEB) simulation.