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 32
Turbo-GMM: FlashAttention-Inspired GPU-Accelerated Gaussian Mixture Model
Expectation-maximization (EM) for Gaussian mixture models (GMMs) requires scoring $N$ data points against $K$ mixture components.Learning the Entropic Relaxation: Stable Coarse-Grid Emulation with Neural Discrete Equilibrium
The ability to emulate complicated and computationally-expensive physical systems in an efficient and stable manner is a popular motivation for scientific machine learning (SciML).Training Autoregressive Language Models on Rounded, Bounded, and Censored Numerical Labels via Exact Likelihood
Numerical labels often specify a set of possible values: a measurement is rounded, a laboratory test reports only a bound, or a program is stopped at a timeout.MetaPOCS: Meta-Learned Multi-Exit Unfolding for Budget-Aware Seismic Data Interpolation
Seismic data interpolation must reconcile reconstruction fidelity with the computational budgets of acquisition quality control and subsequent imaging.End-to-End Stability of Online Active Learning in Large-Scale Neural Systems
Online Active Learning (OAL) aims to extend deep learning from static inference after offline training to continuous adaptation during real-time interaction with a changing physical environment.Cross-Domain Joint-Embedding Pretraining For Heterogeneous Industrial Time Series
Industrial predictive maintenance and manufacturing tasks frequently contain abundant sensor measurements, but with limited labeled data.Semantic Caches for LLM Web Services Leave Their Error Budget Unspent
Web services built on large language models (LLMs) receive many paraphrases of earlier queries, which a semantic cache answers from stored responses.SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
Speculative decoding accelerates memory-bound LLM decoding with a lightweight drafter, and parallel drafters extend this speedup by drafting a whole block in one forward pass.QFacePlacement: From Arbitrary Tensorization to Semantic Spatial Correspondence in Modern Face Verification
Quantum-inspired computer vision often reshapes high-dimensional features into tensors and applies tensor-network models.AttentionIndex: Accelerating Learned Sparse Attention with a Causal Inverted-File Index
Learned sparse attention, used in production models such as DeepSeek-V4 and GLM-5, lets each query attend to only k keys chosen by a lightweight indexer, but the indexer still scores every key in…When Prediction Shapes the Future: A BlueSky Agenda for Reflexive Time Series Analysis
Time-series models are increasingly deployed in operational systems (e.g., inventory management and clinical care) where predictions trigger interventions that alter future observations, producing…On the Convergence of Alternating Regret Matching Algorithms
Alternating updates, that is, where each player is updated in turn, tend to typically perform better in regret matching algorithms than simultaneous updates.Tune the Baseline First: Most of Muon's Scaled Weight Decay Gain Is a Tuning Gap, but Its Small Real Advantage Grows With Model Size
Scaled weight decay for Muon (Muon-SW) has been reported to train language models more efficiently than constant decoupled weight decay, but such comparisons usually reuse one learning-rate (LR) and…PixelBench: Can LLMs Understand and Generate Images Pixel by Pixel?
Large language models (LLMs) can generate visual assets through text-based formats such as SVG and CAD, but these symbolic representations describe images using high-level primitives rather than…Energy-Based Policy Orchestration
Hierarchical control scales robot behavior by separating task-level planning from low-level control.CR-Bench-v2: Evaluating the Real-World Utility of AI Code Review Agents
The rapid growth of automated code generation has created a pressing need for automated code review.Organizational Learning in Materials Discovery Campaigns: Which Databases, Calculations, and Agent Teams Pay Off
More databases can make a materials campaign worse.RLVR Sharpens the Pencil, Not the Mind
Models like DeepSeek-R1 made Reinforcement Learning with Verifiable Rewards (RLVR) famous: reward a model for correct answers and it gets dramatically better at reasoning without being taught how.Beyond $L_\infty$-Norm Sets: Synthesizing Interpretable Non-Uniform Uncertainty Sets for Evaluation-Time State-Adversarial Robustness
Deep reinforcement learning (DRL) agents are vulnerable to perturbations of their observed state inputs.Probing Local Conditional Fit for Diffusion Model Membership Inference
Membership inference determines whether a candidate example was used to train a text-to-image diffusion model and is an important tool for auditing training-data use.