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 121
MS-TTRL: Breaking the Frequency Conflict in Multiple-Solution Test-Time Reinforcement Learning
Scientific, engineering, and mathematical reasoning tasks can admit multiple valid solutions, while exhaustive annotation of the full solution set is often prohibitively costly.Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning
Small language models deployed under cost, latency, or privacy constraints cannot simply switch to larger models when reasoning fails.BiLoCo: Binary Low-Rank Corrections for Post-Training Quantization
Post-training quantization (PTQ) to FP4 has emerged as a key technique for reducing large language model inference cost, especially on Blackwell GPUs, which offer native FP4 tensor core support.Do Halting Heads Really Save Compute in Looped Language Models?
Looped language models run each token through the same layers several times, and each run is one iteration.Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection
Out-of-distribution (OOD) detection is recognized as a critical problem in AI safety.Empirical concentration for chains with infinite memory
Concentration inequalities for time series usually involve unknown quantities measuring dependence.RootDown: Deploying and Benchmarking Models for Beet-Root Detection on Edge Devices
Quality inspection of sugar beets after harvest and storage is critical to preserve sugar content and ensure optimal processing efficiency.ReLEAP: Upcycling Vision Datasets through Cross-Task Unification and Semi-Supervised Annotation
Developing robust vision models requires large amounts of annotated data, especially for tasks involving fine-grained class distinctions under variable environmental conditions.Complementing DINO Features with Image Structure for Part Discovery
Self-supervised Vision Transformers (ViTs) like DINO encode rich semantics, enabling training-free segmentation of objects from the background and discovery of their parts via feature clustering.CoPiT: A conditional Position-induced Transformer for aerodynamic field prediction on unstructured meshes
High-fidelity Reynolds-averaged Navier--Stokes (RANS) simulations remain a standard tool for aerodynamic analysis, yet each solve on an unstructured mesh is computationally expensive, making…DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks
Multi-stage analytical tasks require LLM agents to use intermediate evidence to decide whether to continue, redirect or stop.Supervised Source Separation of Electric Vehicle Interior Noise Using a Hybrid Transformer Architecture
The interior sound of an electric vehicle is a superposition of several distinct noise contributions - wind noise, tire noise, powertrain (electric drive unit and inverter) noise, and…GeoLEON-CLIP: Graph-Anchored Multimodal Contrastive Learning for Geographic Region Representation
Geographic regions are multimodal: satellite imagery captures visual morphology, text conveys human-interpretable semantics, and map structures describe urban context.SKG in Practice: OOD Generalization Cases Across FourDomains
This paper presents the engineering implementation methods of the SKG inference framework and provides complete case studies across four domains.When to Trust Memory: Retrieval-Guided Probabilistic Spatiotemporal Forecasting under Distribution Shift
Spatiotemporal forecasting plays an important role in real-world applications, where probabilistic approaches provide uncertainty estimates for decision-making.TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection
In unsupervised multivariate time series anomaly detection (MTSAD), local variation can inflate reconstruction and forecasting errors, making observation-space discrepancy an unreliable indicator of…Optimal Multiclass Online Regret with Arbitrary Label Spaces
We determine the optimal regret in agnostic multiclass online learning with arbitrary, possibly infinite, label spaces.Detection and Validation of Hidden Subgroup Disparities in Clinical AI
Machine learning (ML) models used in clinical workflows often perform systematically differently across patient groups, raising concerns about equity and patient safety.Acoustic and Lexical Signals for Native Language Identification of Language Learners
Spoken native language (L1) identification for second language learners has traditionally relied on acoustic attributes of speech.KnitTrans: Coordinated Trajectory Transfer for Effective and Efficient LLM Reinforcement Learning
Trajectory transfer from rollout to training affects both learning quality and system efficiency in large language model reinforcement learning (RL).