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 123
Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations
This paper examines speech characteristics of the Austrian National Council members (CMs).Principled Nonlinear Concept Erasure and Steering
Learned representations often encode sensitive attributes, such as gender or race, that may be undesirable or unsafe to retain.Exact Global Minimax Risk near Nonidentification
We study squared-error estimation when a nuisance parameter is unidentified on a submodel but affects a target that vanishes there.Shared Is Not Enough: Predictor Width and Factor Readability Under Masked Latent Prediction
Masked latent prediction methods such as I-JEPA aim to learn predictable features, but what determines which information they retain is less clear.From Parameter Rebasin to Functional Transfer Across Heterogeneous Transformers
Adapting pretrained Transformers to downstream tasks produces task-specific updates that are expensive to reproduce for every model variant.Batched NN 4D-Var: a performant hybrid model framework for the Integrated Forecasting System
Hybrid forecasting systems combining machine learning and numerical weather prediction offer a promising route toward improved forecast skill while preserving physical consistency.Contextual Decision Making: Predictive or Generative
Contextual decision making uses observed covariates to guide decisions under uncertainty.Universal neural network approximation of symmetric polyconvex energies and envelopes
Symmetric polyconvexity provides a sufficient condition for weak lower semicontinuity in small-strain elasticity and a tractable lower bound for the relaxation of non-(quasi)convex energies.Let's Do Turbulence Right: In Space and Time!
The three-dimensional Navier-Stokes equations govern fluid turbulence, a chaotic and non-linear physical phenomenon characterized by complex eddies interacting across vast spatial and temporal scales.Trajectory Matching: Discrete Flow Matching with Structured Actions
The natural units of structured discrete generation are often not independent single-component edits but richer actions: attaching a fragment to a molecule, inserting a node together with an…Interpreting Supervised Pairwise Graph Representations: Local Evidence, Confounding, and Provable Post-hoc Correction
Supervised pairwise graph representations convert pairwise predictive relations into sample-specific graphs, but graph-level accuracy does not by itself show that higher-order topology carries the…Earth embeddings are decomposable records of the land surface
Ecological monitoring, carbon accounting and biodiversity assessment increasingly rely on annual Earth embeddings--learned vectors that compress a year of satellite observation for every ten-meter…Acquisition for Spherical-Linear Bayesian Optimization on the Cube
Recent work demonstrated that executing Bayesian Optimization (BO) using simply a linear surrogate with a clever transformation is enough to approximate the performance of the standard…The Standard Deviation in VICReg Buys a Safety Margin
VICReg prevents collapse with a hinge on the standard deviation of each embedding dimension, and its authors argue from the gradient that a hinge on the variance would fail.WL-SeqVAE: Sequence-Based Graph Generation Using Variational Autoencoders and Weisfeiler-Leman Colors
In this paper, we introduce WL-SeqVAE, a sequence-based variational autoencoder for generating graphs.DT-JEPA: Learning to Predict Future Representations for Decision-Making
Decision Transformer (DT) has demonstrated strong performance in various offline reinforcement learning (RL) tasks by conditioning action generation on expected future returns and historical…Do Language Models Trust Their Own Justifications? A Study on Functional Consistency
Large Language Models (LLMs) have been widely adopted in text classification tasks, where they not only output class predictions but also generate explanations that highlight the tokens deemed most…EMG Tokenization Preserves Movement Information at a Fraction of the Bitrate
Wireless electromyography (EMG) interfaces must balance electrode coverage against transmission bandwidth.Probing the limits of forward screening and inverse design of crystal materials
Crystal materials are designed either by screening known crystals for a target property or by generating new crystals with that property.Score-Preserving Continual Lasso under Task Shift
Continual learning (CL) aims to learn from sequential tasks while mitigating catastrophic forgetting when historical data are no longer accessible.