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 4
Instrumental Variables in Continuous-Time Stochastic Processes
Causal questions often arise in systems that evolve in continuous time.$O(1/n)$ Convergence Rate for RVI $Q$-Learning
We establish finite-time convergence guarantee for synchronous relative value iteration (RVI) $Q$-learning for finite weakly communicating Markov decision processes (MDPs).Randomized and Oracle-Based Feasible Directions Methods for Nonsmooth Nonconvex Constrained Optimization
Minimizing nonsmooth nonconvex objectives over general convex sets using no derivatives of the objective, together with structural access to the constraint set, poses a fundamental geometric…Non-Parametric Mutual Information Estimation with Vine Copulas
We introduce VINE: a non-parametric mutual information (MI) estimator based on simplified D-vine copulas.Equivariant Deep Learning in Direct-Product Space for Electronic-Structure Hamiltonian Prediction
Most existing equivariant architectures for Hamiltonian prediction propagate features in direct-sum spaces of irreducible spherical tensors, whereas the target Hamiltonian is naturally an operator…InfMasking: A Unified Variational Framework for Synergistic Multimodal Learning
Multimodal models are expected to exploit synergistic information, that is, information available only when multiple modalities are observed together.Multimodal Information Interactions Bottleneck for Multimodal Self-Supervised Learning
Multimodal self-supervised learning is challenged by heterogeneity, unequal informativeness, and complex information interactions across multimodal data sources such as images, text, audio, and…Evaluating Language Model Features for Zero-Shot Time-Series Anomaly Detection Under Isolation Assumption
Time-Series Anomaly Detection (TSAD) is a fundamentally challenging task: it is unsupervised, requires high local precision capabilities, and suffers from limited labelled data.Reinforcing What the Student Has Learned: Teacher-Guided On-Policy Distillation
On-policy distillation (OPD) improves language-model reasoning through dense teacher feedback on student-generated responses.We first observe an amplitude disparity in this feedback: on math…Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif Scaffolding
Protein motif scaffolding benchmarks assess whether generative models can build scaffolds around functionally important residues.Extending Reasoning in Typed Decision Models via Looping
Typed decision models choose among a fixed set of answer options in a single forward pass, so unlike generative language models they cannot spend more test-time compute on hard inputs by generating…Comparing Classification and Feature Learning by Analyzing Their Loss Functions in Normalized Spaces with Different Scale Factors
Classification and feature learning are two closely interrelated fundamental tasks.Ordering Multivariate Time Series by Volatility Memory: A Temporal Convolutional Approach to Volatility Heredity
Volatility dynamics can carry information about temporal relationships that is not apparent in the conditional mean.ConvPE: Convolutional Position Embedding Improves Transformers
ConvPE (Convolutional Position Embedding) improves both the performance and efficiency of Transformer models in language modeling, long-context extension, and vision.Foresee to Trade: Forecast-Augmented Policy Optimization for Portfolio Management
Online investment services must translate asset opportunities into investment outcomes for users' accounts, yet the same market opportunity can warrant different account actions.Neural Collapse on Imbalanced Datasets and Open-Set Scenario
Neural collapse (NC) describes the elegant geometric structure that sample features and classifier vectors exhibit when a classification model's loss reaches its minimum.Scaling Laws for SAE Training Data
Activation storage is often a bottleneck in sparse autoencoder (SAE) training.Optimal Learning in Games with Arbitrary Delays: Best-of-Both-Worlds for Self-Play and Adversarial Opponents
We study learning in zero-sum games with delayed feedback.Adapters as Data: The Latent Space of LoRAs
LoRA adapters are usually treated as finished artifacts rather than as a data modality.PBPO: Prefix-Block Policy Optimization for Diffusion Language Models
Diffusion Large Language Models (dLLMs) commonly decode responses by proceeding autoregressively across blocks while iteratively denoising multiple tokens within each block.