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 102
Identities, Not Pairs: Distribution-Free False-Accept Control for Embedding-Based Verification
Embedding-based verification often calibrates a false-accept threshold from all impostor pairs among $m$ identities, although these pairs share identities.Self-Supervised Pretraining for PHM: What Transfers, What Does Not, and What Federating It Costs
Self-supervised pretraining has produced capable time-series foundation models, but its value for Prognostics and Health Management (PHM) has not been measured under leakage-controlled conditions.InterQ-RL: Interaction-Aware Correction of Execution Mismatch in Quantized Agentic RL
Multi-turn agent reinforcement learning (RL) relies on long closed-loop rollouts, making generation and KV-cache costs a major bottleneck.Inference Latency-Aware Tsetlin Machine Training
The Tsetlin Machine (TM) is a logic-based machine learning model well suited to low-latency inference on resource-constrained edge devices.Shared Context, Separate Engines: Stateful Streaming Inference for Multimodal LLMs on Edge SoCs
Edge SoCs combine CPUs, GPUs, and NPUs, yet runtimes for multimodal large language models (MLLMs) keep generation on one engine and leave others idle.Temporal-Difference Calibration of Black-Box Simulators
We develop a derivative-free temporal-difference (TD) framework for calibrating black-box simulators using one-step transitions from a target system and noisy simulator-generated continuation values.CoPE-CGL: Community-aware Prototype Extraction for Replay-Free Continual Graph Learning
Continual graph learning (CGL) maintains models as graphs evolve without retraining from scratch, while mitigating catastrophic forgetting.Beyond Wasserstein Proximity: Finding Better Transfer Sources
Source selection often favors similar data, yet marginal proximity need not identify the most useful pretraining source.Geometric Consistency Based Label-Free Validation for Checkpoint Selection in Audio Active Learning
Audio active learning (AL) trains a classifier at low annotation cost by labeling only an informative fraction of an unlabeled collection over successive rounds.One Megakernel is Not Enough: Predicting Where to Cut for Streaming Inference
We address a fundamental question: How far should kernel fusion extend and which boundaries are worth preserving?Targeted Deep Regression - Initial Applications in Whole-Body Water-Fat MRI in UK Biobank
UK Biobank is a British clinical study which, in addition to large amounts of medical data collected, plans to include detailed Magnetic Resonance Imaging (MRI) examina- tions from 100,000…Should Pseudo-Labels Share Mini-Batches with Labeled Examples? Semi-Supervised Continual Active Learning with Limited Training Cost
Active learning (AL) reduces annotation by querying informative examples.OneEEG: A Unified Signal-Visual Multimodal Language Model with Task-Aware Mixture of Projectors for Multi-Task EEG Understanding
Electroencephalography (EEG) is widely used in clinical assessment, brain-computer interfaces, and cognitive-state analysis, yet EEG modeling remains fragmented across task paradigms.Benchmarking uncertainty quantification for engineering regression under graded distribution shift
Machine learning models in engineering are often used beyond their training conditions, where reliable uncertainty quantification (UQ) matters most.TransECG-SSL: Hybrid Self-Supervised Representation Learning for ECG Arrhythmia Classification
Cross-dataset generalisation remains a major challenge for automated electrocardiogram (ECG) arrhythmia classification because of differences in patient populations, acquisition protocols…Belief-Conditioned Multi-Agent Actor Critic for Decentralized LLM Collaboration
Recent work has explored optimizing LLM collaboration through Multi-Agent Reinforcement Learning (MARL), but many approaches still rely on predefined workflows, limiting efficiency and scalability.The Geometry of Emotion Representations Across Scale, Depth, and Instruction Tuning
We measure the emotion geometry of six LLMs spanning Google's Gemma 2 family.Intent-Preserving Adversarial User Simulation for Multi-Turn Agent Evaluation
Multi-turn agents are commonly evaluated with LLM-based simulated users, which can be overly cooperative and can therefore overestimate an agent's performance.A knowledge-driven nonconvex square-root regularization framework for joint group sparsity and structured smoothness
Structured sparse learning is a leading paradigm for high-dimensional data modeling, as it enables rigorous integration of domain-validated structural priors into the learning process.Prior Predictive Matching for Bayesian LoRA
Bayesian variants of Low-Rank Adaptation (LoRA) provide principled uncertainty estimation when fine-tuning large foundation models, but require specifying the prior over the low-rank weight updates.