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 159
Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis
This study proposes a sketch-to-simulation system to solve handwritten circuit diagrams.KIRA: A Full-Stack Reading Screening System with Dual-Pathway Analysis for Children
Early-grade reading screening is critical for identifying children at risk of reading difficulty.When Do Gaussian Priors Fail? A Latent Geometry Investigation of RL Fine-Tuning
Latent diffusion models almost universally place a Gaussian prior on the VAE latent space.Self-Supervised Tuning of Low-Fidelity Optimization Models via High-Fidelity Feedback
Low-fidelity (LF) optimization models are widely used in large-scale operations because they can be solved efficiently and reliably, but they often exhibit systematic errors relative to…DualHeads: Reward-tilted few-step diffusion made simple
Distilled diffusion models generate high-quality images in a few sampling steps, but aligning them with task requirements and human preferences is difficult.A General Topological Symmetry Index for Critical Orbits In Neural Network Loss Landscapes
A systematic understanding of the global structure of neural-network loss landscapes remains challenging due to their high dimensionality.How Much Gradient Does Truncated Backprop Lose in Looped Transformers?
Looped transformers reuse one block of layers many times and are often trained by backpropagating through only the last k loops.LEAN: Loss-Engineered Modulation of the Model Weight-Sensitivity Distribution for Efficient, Error-Tolerant Neural Networks
The weights of a trained network do not have uniform sensitivity to model accuracy: the 1% most sensitive weights carry about a fifth of the damage a bit flip can do.Actually, All Learnable Distribution Classes Are Privately Learnable
We show that every class of distributions that is learnable up to arbitrarily small target error in total variation distance with finitely many samples is also learnable under ($\varepsilon…RL-IF: Tracking Non-local Training Data Influence for Online Reinforcement Learning
Online reinforcement learning (RL) has achieved significant success in decision-making tasks, but modern online RL remains highly sensitive to the quality of training experience.Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge Recasting
Adapting language models to new domains during post-training risks degrading previously acquired capabilities, a phenomenon commonly known as catastrophic forgetting.CSD: Common-Support Distillation for Cross-Tokenizer Knowledge Transfer
Cross-tokenizer logits distillation enables knowledge transfer across model families, allowing students to learn from stronger or more specialized teachers.Is Refusal Direction Universal across Low-Resourced Languages?
Refusal directions have been shown to transfer cross-lingually with near-perfect effectiveness across safety-aligned languages (Wang et al., 2025), reportedly regardless of resource level.Minimax-Optimal Predictive Flow Matching under Distribution Drift
Flow matching learns a generative velocity field by regression, but under distribution drift a field must be deployed before the current data arrive.Tropical Cyclone Attributes in Sparse Autoencoder Features of an AI Weather Model
Artificial intelligence (AI) weather models now forecast weather events skillfully, but how they represent these events internally remains unknown.JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds
Multi-agent reinforcement learning (MARL) offers a principled way of populating simulated economies with many heterogeneous decision makers.Backtracking Direct, Indirect and Total Effects
Natural direct and indirect effects are defined through cross-world interventional counterfactuals.A Model-Free Continuous-Time RL Algorithm from Discrete-Time Off-Policy Data with End-to-End Guarantees
In this paper, we study continuous-time reinforcement learning, where the state follows an unknown stochastic differential equation but only a fixed off-policy batch of discrete-time transitions is…Query Feedback and Teaching for Stable and Certifiable Language Generation
Language generation in the limit studies whether a learner observing an enumeration of an unknown target language can eventually generate only valid, previously unseen elements.One Policy, Many Styles: Where to Aggregate Preferences for Steerable Humanoid Control?
Modern robotic agents are increasingly expected to support steerable control, where a single policy can adjust its behavioral style at runtime under changing user preferences.