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 107
Instruction Capacity: Behavior and Degradation of Language Models under Controlled Load
The quality with which language models follow instructions falls as the load grows, yet there is still no quantity that expresses the limit of a model in units of load with an uncertainty.Minimax-Optimal Small-Loss Bounds for Online Linear Optimisation on $\ell_p$ Balls
We study full-information online linear optimisation on the unit $\ell_p$ ball in $\mathbb{R}^d$, for fixed $2\le p<\infty$ and losses of dual norm at most one.Beyond Update Counts: A Control Map for Evaluating Test-Time Model Updates
Test-time updating lets a language model change persistent state after training---such as model weights, adapter parameters, or a memory module---before or while answering queries.Dirichlet Process Mixtures within Semiparametric Bayesian Networks: A Novel Conditional Density Estimation Approach
Semiparametric Bayesian networks (SPBNs) are flexible probabilistic graphical models for representing joint distributions of continuous variables through lower-dimensional conditional probability…Scaling and Renormalization in Neural Networks: An Effective Renormalization-Group Description of Grokking
Grokking is a delayed transition from memorization to generalization in deep neural networks (NNs).SuperJEPA: Pretraining with a Supervision-Augmented Joint-Embedding Predictive Architecture for High Energy Physics
Foundation models often obtain powerful results through very large unlabeled training datasets that dwarf available labeled datasets in size, but high energy physics already provides large samples…Symmetry Breaking Is the Price of Finite Capacity
If rotating a problem never changes its answer, one might expect its best model to be rotation-invariant; we show that this fails, predictably and by an exact amount, when capacity is limited.SpatialPC: Deep Computation with Sublinear Local Credit Propagation
On a chain of $N$ states, any local learning rule with bounded communication range needs $Θ(N)$ rounds before the loss can influence the earliest parameters, and this latency is usually attributed…Anytime Valid Confidence Bands for Distribution Functions
Nonparametric inference often requires characterizing an unknown function, such as a cumulative distribution function (CDF), across its entire domain rather than a specific point.Dynamical coarse-graining of neural-network training
Dynamical coarse-graining of neural networks gives macroscopic observables and enables training to be predicted, and controlled in a state space far smaller than the parameter space.Bayesian Evidence Accumulation for Graph-Based Learning in Dynamic Data-Driven Applications Systems
Graph Neural Networks (GNNs) are widely used in modern machine learning, yet most existing frameworks remain fundamentally static, limiting their applicability in Dynamic Data Driven Application…LLM Hallucination Detection via Low-rank Multilinear Decomposition
Large language models (LLMs) frequently generate fluent yet factually incorrect responses, raising concerns about their reliability.Base Models Can Detect Hidden Intentions that Prompted Classifiers Miss
The Persona Selection Model (PSM) posits that post-training selects a persona the model learned during pre-training.Concorde: Geometry-Aware Link Prediction via Decoupled Energy Minimization
Link prediction remains difficult in sparse graphs, where diffusion heuristics lack connectivity and geometric methods suffer spectral instability when coupling learned representations with…Approximation Families and the Statistical Efficiency of Denoising Score Matching
We study score matching over finite-dimensional approximation spaces generated by gradients of eigenfunctions of the infinitesimal generator of a forward diffusion.Structure, Not Sequence: Tracking and Validating Folding Mechanisms in ESMFold's Trunk with Sparse Autoencoders
Structure predictors like ESMFold fold proteins using neural network computation and have transformed structural biology.Three Worlds for the Price of a Logarithm: Baseline-Protected Best-of-Both-Worlds Combinatorial Semi-Bandits
Improving on a baseline requires exploring away from it, precisely where its performance may be lost.Freeze, Don't Clone: Fine-Tuning with Expressive Policies Without Retaining Offline Data
Offline-to-online reinforcement learning uses offline pretraining to accelerate subsequent online learning.What Should an Information Bottleneck Encoder Learn? Separating Representation Learning from Rate Control
The information bottleneck (IB) trades compression of an input $X$ against prediction of a target $Y$ through a multiplier $β=1/λ$, yet each operating point is usually served by training, or fully…Cross-modal Steering Vectors Exist Across Both Image and Text Generation
Are concepts and mechanisms unified across modalities in current AI models, or instead implemented separately for each one?