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 162
OPDArena: Understanding Learning and Forgetting in On-Policy Distillation
On-policy distillation (OPD) is increasingly used for language model post-training, yet how teacher supervision shapes learning and forgetting remains unclear.A "feature ODE" describing the learning behavior of shallow MLPs on simple functions
We study the gradient flow training dynamics of two-layer multi-layer perceptrons (MLPs) on anisotropic Gaussian data.Knowledge Manifold Optimization for Scientific Discovery
The rapid expansion and specialization of scientific literature make it increasingly difficult to identify not only what is known, but where new and still supportable knowledge may emerge.Can Metadata Fix the Gauge? Calibration Turns Sparse Multi-Source Learning from Sparse PCA into Sparse Mean Recovery
Source labels tell us where a sample came from, but not how that source oriented its coordinates.Arbitrage-Free Implied Volatility Surface Reconstruction via Additive Martingales
This work focuses on reconstructing a continuous implied volatility (IV) surface from a small number of option quotes, a fundamental task for option pricing and risk management.LOOP: Recovery-Aligned Iterative Layer Pruning via On-Policy Distillation
Layer-level pruning is attractive for large language model (LLM) deployment as it reduces the model size while preserving a dense architecture that can be efficiently executed on standard hardware.MT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental Learning
As deep neural networks are required to continuously adapt to evolving data, class-incremental learning (CIL) has become an active research area.Progress-Guided Preference Generation for Aligning Generative Control Policies
Generative policies have achieved strong performance in imitation learning tasks, but their success is often constrained by the limited availability of expert demonstrations.Stochastic Tracking of Drifting Affine Fixed Points
Linear stochastic approximation (SA) is widely used to estimate fixed points from noisy observations, but most finite-time analyses assume that the underlying operator remains fixed.Predictive Bandit Curriculum Reinforcement Learning via Gradient-Based Sample Group Discovery
Curriculum learning, which organizes training samples according to their learning priority, has been widely adopted in reinforcement learning to improve training efficiency.Evidence Sufficiency and Model Comparisons in MexRegQA: An Item-Level Audit of Mexican-Spanish Regulatory QA
Similarity-gated coverage does not establish that retrieved evidence contains the facts needed to answer a question.Corrected Block Sparse Spectral Optimization: Exact Models, Finite Identification, and Local Dynamics
The block generalized-power method pairs threshold-based support selection with inexpensive Stiefel updates, but the standard block formulation conflates two nonequivalent objectives and leaves…Learning to Couple: Context-Adaptive Joint Denoising for Diffusion Language Models
Diffusion language models accelerate generation by predicting multiple tokens in parallel, but factorized denoisers treat simultaneous predictions as conditionally independent.Anatomy of Off-Policy Policy Gradient: Importance Sampling, KL Regularization, and Baselines
Reinforcement learning has become a central tool for large language model (LLM) post-training, where policy gradient methods are routinely deployed off-policy, even though vanilla policy gradient…Neural Video Coding under Limited Delay: Theoretical Optimality and System Design
Traditional neural video compression (NVC) methods predominantly follow strictly causal predictive-coding paradigm, treating zero-frame delay as a fixed constraint rather than delay as an explicit…A Calibrated Instrument for Detecting Disposition Drift in Language Models
Before language models are released, they are tested for harmful traits such as willingness to carry out dangerous requests, deception, power seeking, and sycophancy.How Much Does One Wrong Answer Cost? Error Propagation in Constraint Pruning with Noisy LLM Oracles
Constraint pruning saves queries to a large language model (LLM) or another noisy oracle by skipping each yes/no question implied by answers accepted earlier, for example through transitivity.Fundamental Limits of Information-Theoretic Secure Aggregation with User Dropouts in Federated Learning
Secure aggregation enables a server to compute the sum of users' gradients or model updates without revealing individual values.Bayesian Model Discovery with Language Models: Closing the Loop between Hypotheses and Experiments
Scientific model discovery requires proposing candidate models of an unknown system and designing experiments that discriminate among them.Cognitively Decoupled Meta-Induction for Out-of-Distribution Generalization
In-context learning (ICL) tackles downstream tasks conditioned on demonstrations.