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 11
Decouple to Reuse: Fine-Grained Knowledge Augmentation for Time Series Foundation Models
Time series forecasting is critical for demand prediction and resource management in modern Web services, yet applying pretrained Time Series Foundation Models (TSFMs) to downstream tasks remains…FedIA: Instance-Aware Cross-Modal Representations for Federated Prompt Learning
Federated Prompt Learning (FPL) enables parameter-efficient adaptation of pre-trained Vision-Language Models across decentralized clients without exchanging raw data.How Far Can You Steer? Behavior-Capability Frontiers in Contrastive Activation Addition
Activation steering can modify language-model behavior without parameter updates, but behavioral efficacy alone does not determine whether an intervention is usable.Attraction-Ranking Mismatch in Out-of-Distribution Detection: Theory and Evidence from Hamiltonian Feature Dynamics
Attracting features toward learned in-distribution (ID) regions is an intuitive strategy for out-of-distribution (OOD) detection, but does such attraction improve detection?Who Pays for the Knowledge Models Copy? Model Collapse as Rogers' Paradox
Generative models trained on the output of earlier models lose knowledge across generations, rare knowledge first.Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels
There is a fundamental limit to the best prediction error of any model for a given data distribution.TRACK: Multiple Instance Learning for Anti-Money Laundering in Transaction Networks
Anti-money laundering (AML) investigations are organized around accounts, while the suspicious evidence for an account may reside in only a few of its transactions.Act-HiMotif: Hierarchical Daily Activity Schedule Generation via Learned Activity-Structure Motifs
Generating daily activity schedules from individual attributes (e.g., age and income) is valuable for activity-based travel modeling and human behavior simulation.Do Search-Augmented Recommenders Use the Latest Search Episode?
Search-augmented recommenders can use the latest search episode and earlier searches.Impact of Negative Weights on Performance in Reservoir Computing
Reservoir computing provides an efficient framework for time-series prediction because only the readout layer is trained while the recurrent reservoir remains fixed.Alleviating Limited Effectiveness and Multi-Class Collapse in Deep Graph-level Clustering
Given a collection of $N$ graphs, graph-level clustering (GLC) seeks to partition the $N$ graphs into semantically meaningful groups, which serves as a fundamental task in analyzing graph-structured…Softmax Attention with Any Temperature in Fixed Dimension: Matching the Best Known Maximum-Inner-Product Bounds
Attention is central to modern AI models for language, vision, and scientific modeling.Learning From Static Context in Federated Time Series Forecasting
Time series forecasting is shifting from locally trained, per-series models to global models trained across many heterogeneous series, which requires learning what sets the series apart.PRISM-AMC: Replay-Free Continual Learning for Automatic Modulation Classification
Automatic modulation classification (AMC) is a key component of cognitive wireless systems, enabling spectrum awareness and adaptive communication.Offline Learning of Reserve Prices from Censored Bids
We study how a seller can learn a reserve price for a second-price auction from censored historical bid data.Catastrophic Overfitting is Weight Drift the Training Loss Cannot See
Fast adversarial training (FAT) makes robust training affordable by replacing the multi-step attack with a single-step one, but it suffers from catastrophic overfitting (CO): partway through…Shallow Encoding Emits Deep Memories
Hybrid language models interleave a few softmax-attention layers with many linear-attention or state-space layers, so every layer keeps a memory of earlier tokens: a key-value cache or a fixed-size…Many Pixels, One Composition: Self-Supervised Spectra for Specimen-Level Prediction
Can hyperspectral (HS) imaging be used to predict the elemental composition of physical specimens found on the Earth's surface?Learning When to Think Aloud in Latent Reasoning
Latent Chain-of-Thought (CoT) reasoning improves efficiency by shifting intermediate computation into continuous hidden states.From Handcrafted to Generative: RLVR-Optimized Icon Generation for Alexa+
Alexa+ devices with screens display animated icons during conversations to visually reinforce what is being said.