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 42
Dr. No: Feature Steering for Abstention in Vision-Language Models
Large foundation models often answer even when the available visual or textual evidence is insufficient to support a reliable conclusion.ExaTune: Exhaustive Hyperparameter Landscape Exploration at Scale
Hyperparameter optimization (HPO) returns a single optimal configuration, systematically discarding the explored performance landscape that encodes how results depend on configuration choices.Learning Almost Complex and Complex Structures
We study the numerical constructions of almost complex and complex structures on spheres and products of spheres up to real dimension six.INSIGHT-HPC: An Interpretable System Intelligence for Global HPC Telemetry
Modern high-performance computing (HPC) clusters integrate multi-generation CPUs and GPUs, which generate rich, high-dimensional telemetry streams from out-of-band baseboard management controllers…Embedding Semantic Entropy: NLI-Free Semantic Uncertainty Estimation with Geometry-Aware Clustering
Large Language Models (LLMs) often generate fluent yet incorrect responses, making un- certainty estimation important for reliable deployment.The Information Limits of Neural Controlled Differential Equations Under Sparse Observations
Neural controlled differential equations (Neural CDEs) evolve hidden states along continuous paths constructed by interpolating discrete observations.Hardware-Aware Design and Layout Selection in Quantum Reservoir Computing for Insurance Claims Forecasting
Quantum reservoir computing (QRC) processes temporal information through quantum dynamics, but it remains unclear whether small QRC models can forecast real data competitively with classical models…EpiLoRA: Fusing Many LoRA Adapters into Low-Precision GEMMs for Serving and RL
Low-rank adapters (LoRA) let one base model serve many fine-tuned variants: multi-tenant engines keep a single copy of the base and batch the requests of many tenants, each with its own adapter.When Latent Dynamics Meet Data Assimilation: A Benchmark of Koopman-Type Representations
Koopman representations describe nonlinear dynamics through linear evolution in a transformed space, offering an attractive framework for their linear simplicity and generality.Sequential auditing of connected forecast errors under partial observations
Graph forecasting systems often rely on prediction intervals to quantify uncertainty across connected locations, but the true outcomes needed for evaluation may be only partially observed.Accelerating FastDEC Clustering Algorithm with GPUs
Fast Dominance Estimation Clustering (FastDEC) is an efficient variant of Density Peak Clustering (DPC) that achieves high clustering quality through dominance-based density estimation, but remains…Camera Radar LiDAR Fusion via Point-Cloud Projection for Multi-Task Learning
Autonomous vehicles require robust perception systems to operate safely under diverse environmental conditions.We Ran a Research Sprint With AI. The AI Worked. The Research Didn't
Generative AI tools for research are widely deployed, yet individual productivity gains do not guarantee better team research.Do We Still Need Rotation-Invariant Architectures? A Statistical Robustness Benchmark for Point Cloud Classification
A substantial line of work builds rotation invariance directly into point cloud architectures.P$^2$-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors
Multi-teacher on-policy distillation consolidates expert capabilities by supervising student-generated trajectories, whereas task arithmetic offers a training-free alternative through linear…Forget What Comes Next: LLM Unlearning via Statistical Independence
Large language models (LLMs) can memorize and reproduce fragments of their training data, raising privacy and legal concerns that motivate machine unlearning.Sampling Interventional Distributions with Orthogonal MMD Flow
Many causal inference problems require sampling from interventional outcome distributions rather than estimating low-dimensional summaries.Ermakov--Based embeddings as a parameter-free layer for physics-informed neural networks
Evolution equations with time-dependent coefficients force a neural solver to spend capacity on a scale that the equation already determines.Stacking-Based Weighting for Large Language Bayes in M-Open Settings
Large Language Bayes (LLB) transforms a natural language problem description into a collection of candidate probabilistic programs and performs inference within each model, combining their…One Mistake, Three Layers: Persistence Rules Under Depth Correlation
Probing frozen representations layer by layer is now standard practice, but reporting when a signal first becomes decodable requires a rule for reading a depth curve, and the obvious rule is wrong.