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 103
EvoBench: An Evolving, Diagnostic Benchmark Framework for Environmental Modeling
Machine learning models are now widely used to predict environmental variable dynamics in domains like hydrology, climate science, agriculture, and ecology.Multi-Horizon Future Discovery for Physics-Informed Exploration
Exploration in physical control environments requires agents to identify actions whose consequences reveal previously unexplored aspects of the underlying dynamics.XL MIMO Extreme Learning Machines: Wave-Domain Inference with Stacked Metasurfaces
The recently envisioned goal-oriented communications paradigm requires machine learning inference to be performed directly on wirelessly transferred data, by splitting neural network computations…Amplify, Locate, Estimate (ALE) on Rare-Failure Rates of Fine-Tuned LLMs
Safety fine-tuning can make undesirable model behaviors sufficiently rare that measuring their frequency by direct sampling becomes prohibitively expensive.GPDPO: Learning from Reward Conflicts via Group Pareto-Dominance Policy Optimization
Multi-reward reinforcement learning offers a promising framework for aligning large language models (LLMs) with diverse objectives, but conflicting reward signals can induce ambiguous update…Evaluating Bayesian deep learning for robust biomedical time-series classification under distribution shift: A sleep scoring case study
In biomedical time-series classification, machine learning models often suffer from deteriorating accuracy and calibration due to distribution shift.ShutdownMod: Turning Any Trajectory into a Shutdown Evaluation
Theory and experiments suggest that capable AI agents may resist shutdown.Benchmarking Coding Agents under Evolving Requirements
Software development with coding agents often begins with a rough request that users refine after trying the implementation.Minimax Rates for Conditional Generative Learning under Wasserstein Loss
We study minimax rates for conditional generative learning under integrated Wasserstein loss, with Hölder continuous conditional laws and an unrestricted covariate distribution.Query Complexity of Learning Axis-Aligned Partitions
This work establishes the query complexity of learning high-dimensional boxes in the exact query learning setting.When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing
Reinforcement learning (RL) has shown promise for training multimodal agents to reason and use tools.Model reduction in time: Learning flow maps for reducing stochastic dynamical systems in time
Predictions with dynamical systems can be computationally expensive---even with reduced models---because reaching future prediction times can require many sequential time integration steps.Constraint Learning by Optimizing over Trained Neural Networks: A Pragmatic Tutorial
Constraint learning is an emerging paradigm of modeling optimization problems with the help of machine learning.Depth Improves Training-Time Scaling for Difficult Tasks in Deep Linear Networks
Neural scaling laws describe the predictable power-law dependence of model performance on training time, dataset size, and model scale, with the exponents quantifying how performance changes with…S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning
Critic-free methods are widely used in reinforcement learning with verifiable rewards (RLVR) for long chain-of-thought (CoT) reasoning, avoiding difficult and costly critic training.Beyond Modeling Order: Dual-Path Spatiotemporal Representation Learning for Cross-Subject EEG Emotion Recognition
Cross-subject generalization remains a major challenge for EEG-based emotion recognition due to pronounced inter-subject variability in neural activity and emotion-related spatiotemporal patterns.Efficient probabilistic weather forecasting at quarter-degree resolution with two-sided transport attention
High-resolution probabilistic weather forecasting remains computationally demanding.Explainable Prediction of High-Speed Solar Wind Streams driven by Coronal Holes via Topological Data Analysis
High-speed solar wind streams (HSSs) originating from coronal holes (CHs) are an important driver of recurrent geomagnetic activity.Balanced Sampling in Stochastic Multi-objective Bandits
In stochastic multi-objective bandits, Pareto optimal arms may represent different trade-offs among objectives.Multi-Fidelity Training Reshapes Uncertainty Decomposition in Atomistic Models
Multi-fidelity training, which combines abundant low-fidelity data with scarce high-fidelity labels, is increasingly common in atomistic modeling, but its effect on predictive uncertainty remains…