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 207
BOLT: Multi-Bottleneck Bound-Guided Learning for Flexible Job-Shop Scheduling with Time Lags and Resource-Coupled Transport
Flexible job-shop scheduling becomes resource-coupled when a scarce vehicle fleet moves jobs between stations, because the schedule sets the transport waits.TRACE: Transformer Residual Activation Codebook Encoding for Communication-efficient Distributed Edge Inference
Distributed Transformer inference across co-located edge devices is fundamentally communication-bound, as exchanging activations between sequence-parallel partitions dominates inference latency…Generative adversarial networks with Monte Carlo dropout uncertainty quantification for structural health monitoring: Fibre Bragg grating data augmentation comparison in Hawk T1A aircraft
The signal generation capabilities of a novel data augmentation framework are examined in aerospace structures.CF-NODE: Counterfactual Spatial Node Intervention for Test-Time Adaptation Under Domain Shift, Evaluated Across Five Diabetic Retinopathy Datasets
Automated fundus-based diabetic retinopathy (DR) grading can substantially expand screening capacity, but source-trained models degrade sharply across different cameras, clinics, and patient…Rank Measures of Fine-Tuning Updates Need a Noise Baseline
Studies of what fine-tuning does to a language model often summarise the weight update $ΔW$ by its rank.Sparse Autoencoders Can Induce Local Geometry for Mitigating Catastrophic Forgetting
Catastrophic forgetting remains a challenge in supervised continual learning, as adapting to new tasks causes representation drift and loss of previously learned information.Null Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and Interpretability
Automated discovery systems propose scientific explanations and test which to accept.Learnable Splines for Unstructured Neural Operators
Neural operators approximate solution operators of partial differential equations at a fraction of the cost of numerical solvers.Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards
Enhancing the agentic capabilities of Large Language Models (LLMs) to tackle complex software engineering (SWE) and general terminal-usage problems is a pressing challenge.Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss
Running prompt tokens through fewer routed experts during prefill is a simple way to make mixture-of-experts (MoE) serving cheaper, yet it is unclear what this damages.Progressive Misalignment Can Emerge from Benign Recursive Self-Distillation
Training models on their own outputs has attracted widespread attention as a possible route to advance AI capabilities.Has GPT-6-Astra Achieved Embodied Intelligence?
GPT-6-Astra demonstrates a level of competence in robotic manipulation and navigation that challenges the conventional paradigm of building specialized models for individual tasks and embodiments.Upper bounds on the number of causal pieces in spiking neural networks
The input space of single-spike neural networks decomposes into causal pieces, and the number of causal pieces has been shown to provide a lower bound on the approximation error for some spiking…Generative Value Classifier
Q-learning is premised on learning a function to predict the value of a state-action pair, with the goal of using such a function to guide policy improvement.Predicting Privileged Information Effectiveness for On-Policy Self-Distillation
On-policy self-distillation (OPSD) enables large language models (LLMs) to learn from privileged information (PI) without a separate teacher model.Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models
Internet-scale photo collections of real-world landmarks have driven progress in 3D computer vision yet remain highly challenging for modern 3D foundation models (3DFMs) that estimate scene…Source-Aware Dynamic Pricing with Strategic Buyers
In modern commerce, firms and platforms typically use customer features from different sources to personalize prices: some features are verified using seller records or third-party data, while…Learning smooth dynamics via Kinematic Interpolants
Inferring dynamics from real-world experimental data is inherently ambiguous, as many plausible dynamical systems can explain the same positional observations at measurement times.Learning the Shared Latent Structure of Cryo-EM Inverse Problems
Understanding biomolecular function requires characterizing three-dimensional structure and conformational variability, for which cryogenic electron microscopy (cryo-EM) is a powerful tool.Don't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks
The web is not static or uniform.