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 156
Claims of emergence in AI should be grounded in information decomposition
When a language model develops capabilities not traceable to its individual components, when a multi-agent AI system outperforms each agent on its own, or when a human-AI pair succeeds where either…Geometry-Agnostic Data-Driven Discovery of Extreme Scenarios
We introduce a two-stage data-driven neural framework for discovering dynamically admissible extreme scenarios.Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural Networks
Deep State-Space Models (Deep SSMs) have shown promising performance and computational benefits in processing of time-series data with complex temporal dependencies.Present but Hard to Read: Probing Latent Reasoning with Minimal Pairs
Probing studies of latent reasoning often read a model's state where the answer begins and take a failed probe as evidence that a value is absent.BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models
For efficient deployment of large language models (LLMs), methods of ultra-low-bit backbones reduce weight storage, memory traffic, and linear-layer execution cost, while multi-token prediction…ECG for laboratory values:A comprehensive physiological and technical analysis
Laboratory measurements are essential for clinical decision making but typically require invasive blood sampling.Variance Reduction with Delayed Feedback for Non-Convex Optimization
We study variance reduction for non-convex optimization when gradient evaluations return with a delay.GraphCast-Mamba: Learning Non-Markovian Corrections for Weather Forecasting
Unresolved atmospheric processes can introduce history dependence beyond the short input windows used by many weather forecasting models.Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks
Discrete diffusion models iteratively denoise a noisy sequence of categorical data such as text, enabling any-order generation with self-correction and in-filling capabilities.Discount Yourself: Self-inclusive Freshness-weighted Gossip for Decentralised Learning under Client Outages
Decentralised federated learning (DFL) trains personalised models on devices that average with their neighbours rather than with a central server.Learning Computational Structure for Sample-Efficient Prediction
Statistical learning in high dimensions suffers from the curse of dimensionality.When Do LLMs Help with Feature Selection? A Systematic Empirical Study
Large language models (LLMs) can leverage semantic feature names alongside summary statistics for tabular feature selection, yet it remains unclear when such information improves subset selection…Convergence of stochastic gradient descent for learning linear neural networks
Stochastic gradient descent (SGD) is the cornerstone of modern deep learning, yet its theoretical convergence properties remain poorly understood in non-convex settings.OptScientist: Automated Discovery of Optimization Laws
Many scientific phenomena are best understood as outcomes of underlying optimization problems, yet automated scientific discovery has largely focused on recovering equations that describe observed…Asymmetric Bidirectional Predictive Dynamics in Google Search and COVID-19 Time Series: A Multi-Horizon Forecast-Error Analysis
Online search activity is widely used as a digital trace of information seeking during epidemics, but its predictive value is often reduced to correlation, a selected lag, or a single forecast-error…The Dynamics of Collapse and Recovery in Clustered Federated Learning
Clustered federated learning (CFL) can suffer from cluster collapse.Continual Concept Personalization in Diffusion Models via Residual-Space Adaptation
Text-to-image personalization aims to equip pretrained diffusion models with the ability to learn user-specific concepts from only a few reference images.Evolving Semantic Indexes for Generative Retrieval
Generative retrieval (GR) casts search and recommendation as autoregressive generation of discrete semantic identifiers (SIDs).The Token-Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per Token
Energy-efficient deployment of large language models requires understanding how model architecture, hardware, and serving settings shape energy per generated token.Continuous-Time Policy Gradient from Discrete Data: Convergence Analysis and Model-Free Algorithms
Continuous-time reinforcement learning seeks an optimal policy under unknown dynamics driven by stochastic differential equations using observations collected at discrete times.