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 90
Online gas classification at the edge
Field applications in chemical sensing, from portable safety monitors to mobile robots, require models that are lightweight, fast to respond, and can be recalibrated from limited labelled data.Meta Models: Models that Model Learning
Every neural-network training run produces not only a model, but also evidence about how models learn.Compote: Collapse-Resistant Multiple Hypothesis Learning For Sequential Recommendation
Next-item prediction is inherently ambiguous: a single interaction history often admits multiple plausible continuations across distinct catalogue regions.From Ethernet to Wi-Fi: Flow Feature Selection and Construction for Traffic Classification
Flow-based traffic classifiers trained on Ethernet data may lose accuracy when applied to Wi-Fi traffic.V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models
Embedding-level scaling expands the capacity of language models through lookup-based memory rather than by increasing model depth, width, or dense computation.Crop Yield Prediction Using Regression Models: A Comparative Evaluation of Model Performance
Reliable crop-yield prediction can support agricultural planning and resource allocation.Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception
Multimodal perception forms the foundation of multimodal intelligence.Blindfold: Keeping the Audit Coin Secret from LLM Agents
Audit-based certification bounds the violation rate of an LLM agent by auditing a random fraction $\varepsilon$ of actions and reweighting the audited labels; its validity is meant to rest only on…Quantized Edge Inference of a Self-Supervised SAR-Optical Encoder on Commodity x86 Hardware
Self-supervised vision transformers are increasingly used as reusable encoders for Earth observation, but their inference cost on the hardware available in the field is rarely characterized.Exploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization
Direct Preference Optimization (DPO) typically relies on preference pairs generated from diverse model pools and ranked by an external LLM judge.EnergyCal: Taming Loss Spikes in Muon-Family Optimizers for Sparse MoE Training
Sparse mixture-of-experts (MoE) language-model training can exhibit large loss spikes with Muon-family optimizers.Systematic Morphometric Brain Autoencoding for Representation Learning in Neurodegenerative Diseases
Early identification of neurodegenerative disorders using structural T1-weighted MRI is essential for timely clinical intervention, yet supervised deep learning models often struggle to generalize…On the Sparsity of Direct Preference Optimization: Weight Disentanglement in the NTK Regime
Direct Preference Optimization (DPO) has been widely adopted for aligning language models with human preferences.Self-Regularized Flow Language Models
We introduce SERF (Self-Regularized Flow Language Models), a simple self-supervised framework for improving continuous diffusion language models by exploiting the denoising trajectory itself.Prospector: learning a compact graph traversal policy for scientific reasoning
Scientific reasoning in specialized engineering fields depends on knowledge scattered across the literature, often proprietary and absent from frontier LLM training data.Mechanistic Failure Modes of Weight Pruning in Transformer Language Models
Pruned language models are judged almost entirely by accuracy and perplexity, which assumes that preserved output behaviour implies preserved internal computation.Generative Replay for Equilibrium Propagation: Toward Edge-Friendly Continual Learning in Hopfield Networks
Equilibrium Propagation (EqProp) offers a biologically grounded and hardware-aligned alternative to backpropagation for training Hopfield Networks.Beyond Parameter Protection: Fisher-Shaped EWC for Replay-Free Continual Learning
In replay-free continual learning, Elastic Weight Consolidation (EWC) uses Fisher information matrix (FIM) to protect acquired knowledge by penalizing changes to historically important parameters.Variational Optimal Control for Diffusion Guidance
We present a variational control framework that connects sampling-time guidance and reward-based model adaptation through a shared Jacobian pullback.Physics-Guided Flow Matching: A Generative AI Framework for Global Total Electron Content Forecasting
Accurate forecasting of global total electron content (TEC) is important for space weather monitoring and the reliable operation of satellite communication and navigation systems.