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 147
How Prompt Style Affects AI Accuracy and Speed in Competitive Programming
Large language models are increasingly used in competitive programming, and their outputs are sensitive to how a prompt is phrased.GANet: A Lightweight Group Attention Network for Plant Disease Identification on Embedded Systems
Global warming and climate change are major catalysts for plant diseases, significantly affecting food production worldwide.Benchmarking Model Compression Techniques Across Heterogeneous Edge Platforms: A Predictive Maintenance Use Case for Rotating Machinery
To enable Industry 5.0, where autonomous systems are widely adopted and integrated with people to promote sustainable development in industries, it is imperative to adapt complex deep learning…Automated screening of privacy risks in medical AI
Medical artificial intelligence (AI) models are often shared without their training data, assuming this protects the patients who contributed them.Edit, Don't Imitate: Minimal-Edit On-Policy Distillation for Multimodal Reasoning
Visual mathematical reasoning can fail before reasoning begins: when a vision-language model (VLM) misreads a diagram, subsequent reasoning proceeds from false premises.A Quadratic Lens on Muon's Polar Update: Benefits, Pitfalls, and the Role of Newton-Schulz
Muon updates matrix-valued parameters along approximately orthogonalized directions and often trains large language models faster than AdamW, yet it remains unclear when and why orthogonalization…SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents
Coding agents spend substantial computation generating actions and processing long interaction histories.Generalizing Metropolis-Hastings for DAG Sampling
A fundamental challenge in Bayesian network structure learning lies in efficiently approximating the posterior distribution of directed acyclic graphs (DAGs).GAV: A scientific experimentation environment for PDE agents
Reliable feedback is essential for coding agents to develop programs for partial differential equations (PDEs).EgoHand: Monocular 3D Hand Reconstruction from Egocentric Video
We introduce EgoHand, a monocular 3D hand reconstruction model that achieves state-of-the-art performance on egocentric video.SciFusion: Physics-Guided Compositional Diffusion for Multimodal 3D Scientific Image Generation
Existing 3D generative approaches are typically developed for individual imaging modalities, requiring substantial modality-specific data and limiting their ability to exploit shared structure…TerraTransfer++: Demonstration-Free End-to-End Planner
End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments.Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications
In recent years, Spiking Neural Networks (SNNs) have gained massive attention as an energy-efficient neural computing paradigm due to their event-driven and sparse computing capability.AQL-Lite: Enabling Efficient Knowledge Acquisition for Arabic LLMs via Data-Centric Continual Pretraining
Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT).On the Adversarial Vulnerability of Neural Receivers with Unrolled LDPC Decoders
Neural receivers for 5G New Radio (NR) match classical model-based receivers in link-level performance, but their robustness to adversarial perturbations at the receiver input remains underexplored.Consistency Is Not Validity: Self-Rewarded Moral Argumentation Makes Language Models Decisive but Pliable
LLMs are increasingly consulted for moral judgment.Route-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs
Large language models often apply complex reasoning indiscriminately, leading to overthinking on simple tasks and underthinking on harder ones.CTRL-FM: Inference-Time Structural Control for Flow-Based Virtual Sensing under Long-Horizon Node Outages
Long-horizon node outages are harder than conventional missing-value imputation because complete sensor trajectories remain unobserved for extended periods, while the usefulness of spatial and…Probing and Steering for Safety-Relevant Behaviours in Large Language Models
Activation probes are computed directions in a language model's residual stream, used both to detect safety-relevant behaviours and, by adding their direction back into the stream, to steer them.Bayesian Fixed-Confidence Best-Arm Identification with Abstention
We study the Bayesian fixed-confidence best-arm identification problem in which a learner can abstain from making a terminal recommendation.