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 218
CASI: Credit Assignment via Set Intervention for Agentic Retrieval
Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the resulting set.MMLA-RSI: Recursive Self-Improvement through RTT and RTMA
An agent can improve its behavior within an unresolved problem by changing how it acts and which experience it retains.SpectrumQuant: Spectrum Alignment for LLM Quantization
Orthogonal transforms have emerged as an effective tool for low-bit quantization of large language models (LLMs), as they reshape activation distributions without changing the underlying model…Extreme-Scale Super-Resolution of Homogeneous Turbulence from a Single Realization
Homogeneous turbulent flows exhibit recurring multiscale structures across spatially separated regions, suggesting that a single flow realization may contain sufficient information to learn…Efficient Test-Time Adaptation For Robot Policies
Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload changes, sensing degradation), and retraining or…Comparative Evaluation of Deep-Learning based DoA Estimators for Real-Time ISAC Beamforming
Integrated Sensing and Communication (ISAC) systems rely on accurate Direction-of-Arrival (DoA) estimation for effective beamforming and spectral-efficiency enhancement.Are We Overthinking One-Step Generation?
Diffusion and flow matching are now dominant frameworks for generative modeling in continuous domains, but they typically require multiple network evaluations at inference.Training Dynamics of Transformers on Unbounded Inputs: Attention Learning Can Lag Output Layer Learning
The success of transformers is attributed to several factors, including their capacity to express formal languages over variable-length inputs, and ability of the attention mechanism to focus on…When Does Task-Aware Imputation Matter? An Analysis of Robustness Under Train-Test Mismatch
Missing data is a pervasive challenge in machine learning, often degrading predictive performance and complicating model deployment.Non-asymptotic Convergence of Average-reward Q-learning with Options
We study the finite-sample convergence of Q-learning algorithms for the average-reward formulation of Reinforcement Learning (RL) with options.NeuroDETR: Multiscale Discrete Spatiotemporal Tokenization for Asynchronous EEG Event Detection
Asynchronous EEG event detection supports practical brain-computer interfaces by identifying event classes and temporal boundaries directly from continuous recordings without predefined event…Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry
Preference optimization ranks final answers and trajectory RL maximizes aggregate returns, yet neither credits the local change that turns a flawed reasoning state into a better one.Beyond Expert Rankings: Contrast Calibration for Mixed-Precision MoE Quantization
Mixture-of-experts (MoE) language models activate only a few experts per token, yet all expert weights must be stored.Fractional is Better: Learnable Derivative Orders in Neural Operator Learning
Neural operators learn mappings between function spaces, enabling fast surrogate solutions to partial differential equations.ReAl: Refine neural operators via aligning dynamical flow
Neural partial differential equation (PDE) surrogates trained with mean squared error (MSE) can capture dominant dynamics but often lose high-frequency information and fine-scale structures.Hypothesis Selection via Weighted Medians
Given $n$ distributions (hypotheses) $\mathcal H=\{H_1,\ldots,H_n\}$ and samples from an unknown target distribution $P$, proper hypothesis selection seeks a distribution whose total variation…FOLD: Position-Free Far Memory with Local Order for Long-Context Speculative Decoding
Speculative decoding accelerates LLM generation through lightweight drafting and parallel verification.From Human Corrections to Learned Segmentations: A Critical Mathematical Review of Information, Learning, and Human Effort
When does a human correction become useful learning, and what establishes better segmentation at matched human effort?Cortex: Consolidating Context into Parametric Memory
Context can improve large language model performance, but these gains may be lost after context removal.HRTF Upsampling and Personalization via Neural Operators
Head-related transfer function (HRTF) spatial upsampling from sparse measurements is a fundamental challenge in personalized binaural audio.