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 84
UnEZ: A Fully Unsupervised Self-Templating Neural Network for Redshift and Line Strength Estimation
As spectroscopic surveys grow, estimating galaxy properties such as metallicity, star formation rate, and redshift becomes computationally cumbersome.Discovering Jailbreaks via Curriculum of Models
Automated jailbreak discovery aims to find prompts that elicit prohibited behaviors from safety-trained language models, helping developers identify vulnerabilities before deployment.What to randomize matters: a controlled study of volume, axis and representation in low-data molecular generation
Chemical language models can struggle to generate new molecules when trained on small datasets, where a model may reproduce training examples rather than learn a useful generative distribution.Discovery of Diverse and Realistic Financial Tail-Risk Using Generative Flow Networks
Accurate modeling of rare, high-impact financial events is essential for robust risk management.Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training
In many settings where LLM post-training is desirable, high-quality answers are recognizable but difficult to score with explicit rewards.Contextual Embeddings Beyond the Gold Chunk
Contextual embeddings represent chunks of a document with respect to the document's global context.Where You Inject Matters: The Trust Region Effect in LLM Agents
LLM agents are increasingly adopted in long-horizon tasks and interact with diverse external environments.Geometric Time Score Estimators: Bridging Self-Predictive Representations and Generative Occupancy Models For Reinforcement Learning
In reinforcement learning (RL), temporal reasoning is essential for estimating the density of future outcomes under a policy's occupancy measure.Structural-Test Geometry as an Inductive Bias for Partially Observable World Models
Predictive world-model objectives need not organize latent histories according to distinctions required for later control.Lev-3B: A Data Recipe for Compact Probabilistic Log Decision Models
Many log-analysis tasks involve choosing among known options, such as detecting anomalous sessions or identifying attack techniques, and benefit from calibrated probabilities.TrussTutor-Bench: Benchmarking large language models on solution accuracy, sycophancy, and error detection in statics
Large language models (LLMs) have rapidly become a default source of help for students in science and engineering courses.Memorization Capacity of Invariant Convolutional Neural Nets
Neural networks are powerful memorizers which are often able to interpolate their training data even when the labels have been randomized.Optimization-based lane-changing trajectory planning in mixed traffic with embedded input convex neural networks
Lane-changing (LC) maneuvers are highly challenging vehicle interactions, with substantial implications for traffic safety and efficiency.Planned Restlessness: Delayed Meta Bandits with Budgets
We study episodic finite-horizon Bayesian bandits, or meta-bandits, with independent arms.Communication-Efficient Clustered Federated Learning in Non-IID Wireless Networks
Current and emerging mobile networks face increasing privacy, scalability, and performance challenges as distributed learning becomes essential for advanced 6G services.The Utility of Physics-Informed Machine Learning in Solar Power Production Forecasting
Physics-informed machine learning (PIML) and hybrid modeling have attracted significant attention as approaches for combining physical knowledge with the flexibility of deep learning.Beyond Passing Tests: A Systematic Review and Controlled Re-evaluation of Techniques for Improving the Quality of LLM-Generated Code
Large language models pass most functional-correctness benchmarks, but passing tests says little about whether their code is readable, efficient or secure.Why Speculative Decoding Works Better Than Predicted on Sparse MoE Models
Speculative decoding (SD) accelerates autoregressive inference by leveraging the memory bound nature of decoding, verifying multiple draft tokens in a single forward pass.Benchmarking Graph Neural Networks for AC Power Flow: The Role of Inductive Biases and Physical Constraints
Fast and accurate models for AC power flow (ACPF) are increasingly important as modern electrical grids require more frequent system analyses.Rethinking GFlowNet Training: Negative Reinforce Dynamics
Generative Flow Networks (GFlowNets) are models that learn to sample discrete objects proportional to a target reward.