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 49
Same Function, Different Gradients: Evaluating Gradient Reliability under Reparameterization
Gradients are no longer used only to train models: Gradient magnitudes are now measurement instruments, used to rank attention heads for pruning, to decide per-example clipping in private training…Rare Event Constrained Reinforcement Learning with Large Deviations
We study finite-horizon reinforcement learning with a safety constraint on the probability of reaching a failure set.Fragility Is Not Reducible to Hardness: Conditional Causal Difficulty for LLMs
Large language models show large and seemingly arbitrary performance drops when a task is rewritten in ways that leave its requirements untouched.Large Geometry Models Are Priors For Fast Physics Pretraining
Language and vision models became data-efficient by pretraining on plentiful unlabelled data; physical field models have such data, over ten million 3D shapes, but geometry pretraining designs its…Back to the Future: Predicting Long-Horizon Dynamics with Retrospective Correction for Disturbance-Aware Retrieval
Retrieving objects from densely packed storage requires anticipating how contact disturbs surrounding objects when limited clearance prevents lifting the target over clutter.ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost
Harness optimization can substantially improve LLM agents without modifying model weights, but existing methods primarily optimize response quality.Black Hole Love Numbers with Physics-Informed Neural Networks
We develop and validate a physics-informed neural network (PINN) framework for computing the tidal Love numbers of black holes directly from their perturbation equations.Reduced Cost Influence Functions for Predict-then-Optimize under Noisy Data
Machine learning models deployed in decision-making pipelines, from vehicle routing to dynamic pricing to clinical decision support, must remain reliable in the face of low-quality training data.HQNN-CL: Regime-Aware Hybrid Quantum Neural Network with Continual Learning for Financial Forecasting
Financial time-series forecasting is still difficult owing to the non-stationary nature of the market, regime changes, and catastrophic forgetting, which makes conventional deep learning models hard…Bernoulli On-Policy Distillation: Don't Ignore High-Confidence Student Tokens
On-policy distillation (OPD) trains a student language model on its own trajectories using token-level supervision from a stronger teacher.NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale
Scaling computer-use agents from individual actions to complex software work requires experience that connects decisions to complete outcomes.Order-Only On-Policy Distillation
On-policy distillation (OPD) trains a student on its own generations by matching the teacher's token probabilities.CNN-Based Retinal OCT Classification: Research Gap Analysis and a From-Scratch Baseline, ED126-A
Automated classification of retinal pathologies from Optical Coherence Tomography (OCT) images remains challenging because diagnostically relevant morphological patterns may exhibit substantial…Testing concept-level audits of melanoma classifiers with diffusion counterfactuals and matched positive controls
Concept-based explanations of melanoma classifiers are rarely tested against controls with known targets.Conditional Calibration Contracts under Coupled Load: A Branch-Aware Audit of Switched Inference
Bursty serving changes both queue states and the population selected for each model.Bounded Retained History in a Proxy Flow Replay: A Mixed Predictive Pilot and an Allocation Study
We examine bounded retained history through a frozen predictive pilot and a subsequent allocation study on a curated UNSW-NB15 flow mirror.Mesh2Shell Neural Operator for Inverse Shape Optimization
Physics-driven design seeks high-performing geometries, which need not conform to a learned shape category.TSSDA: An Autonomous Agent for Constructing a Time-Series Text-to-SQL Benchmark
As agents increasingly undertake data querying, Text-to-SQL serves as a foundational capability for database access.Adversarial Robustness of Retrieval-Based Fact-Checking: Detecting and Mitigating Evidence Contamination
Retrieval-based fact-checking systems ground verification in large document collections, creating a critical vulnerability: adversarial evidence contamination.GatedV: Self-Gated Values for Transformer Language Models
Standard attention forms query (Q), key (K), and value (V) matrices through learned linear projections of input hidden states.