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 6
CoRD: Coupled Rollouts Fill the Blind Spot of On-Policy Distillation
On-policy distillation trains a student on its own rollouts, so states the teacher would reach but the student does not are seldom supervised.Tight Asymptotic Bounds on the Maximum Number of Linear Regions of Piecewise-Linear Kolmogorov--Arnold networks
Schoots et al.~\citep{schoots2025relating} (AISTATS 2025) established a generally loose upper bound on the number of linear regions of continuous piecewise-linear (CPWL) Kolmogorov--Arnold networks…QRAE: Query-Relevant Attention Entropy for Context Compression in DeepSearch Agents
DeepSearch LLM agents repeatedly search and carry retrieved sources into subsequent reasoning steps.Towards Multiscale Molecular Representation Learning through Geometry-Based Fragmentation for Polymer Property Prediction
It is well established that molecular substructures can contribute unequally to chemical and physical properties, with specific motifs or side chains often playing dominant roles.Learning Dynamics of On-Policy Distillation
On-policy distillation (OPD) is emerging as an important paradigm for language-model post-training, combining dense teacher supervision with training on student-generated trajectories.GTAFL: Addressing Test-Agnostic Long-Tailed Federated Learning in Medical Image
In healthcare, protecting patient privacy is crucial due to the sensitivity of medical data and its extensive accessibility.Reproducing Kernel (Quasi-)Banach Spaces with the $\ell^p$ Coefficient Norms
This paper advances the theory of reproducing kernel Banach spaces (RKBSs) by investigating the general $\ell^p$ regularization framework, with a particular focus on the non-convex regime $0<p<1$.Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees
Modern classifiers remain sensitive to small input perturbations, while strong model-agnostic robustness certificates such as randomized smoothing are often too expensive for deployment, requiring…KeHoSu: Keyed Homoglyph Substitution for Authenticated Text Provenance over Copy-Paste Channels
Nowadays, large language models produce text at scale, and much of it is redistributed across platforms.Performance metrics in machine learning: a scenario-based guide from the confusion matrix to calibration, regression and uncertainty
Performance metrics can yield different conclusions from the same predictions.Can an LLM Actually Reason and Program about Neural Network's Weights or is it just memorization on steroids? Exploring "Weight-Space Programming"
Large language models (LLMs) have recently been reported to read and write the raw weights of neural networks directly, a capability termed weight-space programming.Optimal Competitive Ratios for Chasing Convex Functions with Quadratic Growth
Chasing convex function has attracted much attention in recent years, which can be formulated as a game between a learner and an adversary.DictLLM: Post-training Compression of Large Language Model with Dictionary Kernels
Efficient deployment of large language models (LLMs) on mobile devices requires balancing performance with compute and memory constraints.Value or Attention: Investigating Layer-wise Relevance Propagation for Graph Attention Networks
Graph Attention Networks (GATs) are increasingly used in domains where scientists need to read a model's reasoning, from medicine to materials science, yet the routing they learn remains opaque to…SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization
Mixture-of-Experts (MoE) models route each token to a few of many experts, yet what an individual expert is responsible for remains unsettled.Gabor Gabor: E-Gaborformer, a Strictly Causal Speech Recognizer with Gabor-Dictionary Convolutions and Delta-Rule Memory
Real-time voice agents need a speech recognizer that never waits for future audio and whose memory per call does not grow with the length of the call.Gradient Boosting for Efficient Rank Discovery in Tensor Network Kernel Machines
Tensor network kernel machines (TNKMs) combine nonlinear features with low-rank tensor representations to model complex relationships efficiently.PersonaAgent: Retrieval-Augmented Transaction Anomaly Scoring with Refreshable Multi-Entity Persona Memory
In large-scale payment networks, entities (card, merchant, etc.) and their interactions play a key role in transaction anomaly detection.Identifying Neural Dynamics Using Nonlinear Interventional State Space Models
State-space models (SSMs) recover low-dimensional latent dynamics from high-dimensional observations, but latents are generally not identifiable from observational data alone.How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels
Anomaly detection (AD) is often framed as a representation-learning problem, where strong performance is expected to require learned features or AD-specific optimization.