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 114
From Slices to Volumes: Comparing 2D, 2.5D, and 3D Residual Networks for Pulmonary Nodule Malignancy-Risk Classification
To compare 2D, 2.5D, and 3D residual networks for pulmonary nodule malignancy-risk classification and evaluate momentum-contrast pretraining, mild augmentation, and exclusion of indeterminate ratings.Knowledge distillation across teacher architectures for compact diabetic retinopathy grading
Diabetic retinopathy grading from retinal fundus photographs is important but difficult to deploy on resource-constrained hardware.h1: A Taste of the Bitter Lesson in Automated Theorem Proving
While progress in informal mathematics has come largely from scaling the chain-of-thought and agentic reasoning of frontier language models, formal theorem proving has increasingly relied on…Condition-Enhanced Generative Adversarial Network for Aerodynamic Configuration Design of Commercial Aircraft
Generative machine learning provides an end-to-end framework for aerodynamic design optimization by generating diverse aerodynamic configurations conditioned on target performance.Generalization in Learning: Eyring Formula and Predator-prey Model
In this work, generalization in machine learning is investigated using a predator-prey model.Data-driven Discovery of Lie Symmetries and First Integrals with Latent ODEs
We present LatentLieODE, a novel neural ODE method to discover linear Lie symmetries and first integrals of the learned dynamics from timeseries observations such as video inputs.One Call Ahead: Packed Self-Speculative Decoding with Diffusion Drafting
Autoregressive (AR) language models generate tokens sequentially, so generating long outputs is costly.The Cost of an Unknown Horizon for the Last Iterate of Clipped SGD under Heavy-Tailed Noise
Training is often stopped at a data-dependent time, so guarantees for the last iterate must hold at all times simultaneously.Faithful Federated Tabular Data Synthesis
Synthetic data is an important data source in the AI era.COPE: Composable Performance Emulation for Mixture-of-Experts Offloading Policies
As LLMs scale, mixture-of-experts (MoE) architectures increase model capacity while keeping per-token computation manageable through sparse expert activation.Benchmarking System One Models for Time-Series Decision Making: A Case Study of Jev
Time-series tasks require both accurate predictions and fast decisions.Performance Gaps Between Open-Loop, Certainty-Equivalent, and Optimal Control Under Action-Dependent Observations
In dynamical systems, feedback can improve performance by allowing decisions to depend on past observations, rather than being designed a priori.Online Covariance Estimation for Averaged Stochastic Gradient Descent on Riemannian Manifolds
We study online inference for averaged Riemannian stochastic gradient descent (RSGD) when the unknown parameter lies on a manifold.An Empirical Study of Reinforcement Learning Scaling Laws
The discovery of scaling laws enables prediction of the performance, the optimal resource allocation strategy, and the best hyperparameter configuration of a large-scale training job based on…Exact Unlearning After Data Curation
Training pipelines often remove similar examples before fitting a model.Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering
Multi-trigger backdoor attacks, in which heterogeneous trigger mechanisms (e.g., patch, blend, warping, and the latent-domain Spy-Watermark) coexist within a single poisoned model, cannot be…Adaptive Transfer of Representational Signatures for LLM Reliability Detection
Large language models (LLMs) are reported to be susceptible to reliability issues including hallucinations and reasoning errors.From Intelligence to Autonomy: Foundations and Construction of Autonomous Agents for Future Intelligent Systems
Artificial intelligence is moving from one-off perception and generation tasks toward long-term planning, tool use, and interaction with real environments.FG-ConvNO: A Geometry-Aware Neural Operator for Propeller CFD Prediction
Computational Fluid Dynamics (CFD) is essential in contemporary engineering design, yet it remains expensive to compute and can take thousands of CPU/GPU hours or more for a single high-fidelity…LegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery
Equation discovery solvers often use different data interfaces, equation representations and evaluation criteria, making their results difficult to compare.