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 230
Uncertainty Evaluation: Bridging Machine Learning and Measurement Science
Reliable uncertainty evaluation is essential for assessing the trustworthiness of machine learning (ML) predictions, particularly in safety-critical applications.WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
Scaling interactive environments is important for training long-horizon agents through reinforcement learning.Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach
Selection bias is a difficult yet widespread problem in causal discovery, occurring whenever non-random selection processes lead to data that is not representative of the underlying populations.Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents
Long-horizon agents often struggle to recover from failures whose causes lie several steps earlier, beyond what local reflection or backtracking can resolve.Same Function, Different Trajectory: No Standard Optimizer Is Equivariant to Transformer Reparameterization
We show that two Transformers representing the same function can follow different training trajectories.ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch
Autoresearch systems increasingly undertake entire research projects.From Spectral Saliency to Finite Deletion: Evaluating Selective Language Model Edits
Deleting singular components offers a precise way to remove a capability from a language model, yet the first-order spectral saliency used to rank components predicts only a local loss change…The Effect of Layer Ordering in Hybrid Architectures
Hybrid attention is rapidly becoming the dominant architectural choice for frontier models.A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge
Large language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a scalable alternative when human evaluation is too…SYNPRED: A Synergistic Approach to Multimodal Learning for Clinical Prediction
Multimodal medical data captures complementary aspects of disease.When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features
Graph Neural Networks (GNNs) commonly assume that node features are fully observed, despite missing features being pervasive in real-world applications.H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression
Training-free diffusion-based compression methods repurpose the generative priors of a diffusion or a flow model to compress data without retraining them as task-specific codecs.Distance Prediction for Quantum Codes
The distance of a quantum code is a fundamental metric that dictates its error-correction capability.Revisiting Error Feedback for Model Quantization
We study causal error-feedback coefficients as design variables for model quantization.Learning a Group Element from Its Action: Galois Correspondences, Optimal ERM, and an Abel-Ruffini Threshold for the Natarajan Dimension
We study learning an unknown element $g$ of a group acting with finite orbits on a countable set, from examples $(x,gx)$.When Do Learned Blocks Preserve Causal Meaning? Block Identifiability and Constructive Causal Abstractions
Standard identifiability theory assumes one-dimensional latent factors, but learned representations can encode latent information across multidimensional blocks whose internal coordinates are not…LoOPSD: On-Policy Self-Distillation with Looped Teachers
On-policy self-distillation improves a model using guidance from the model itself, but it still requires a teacher that provides more useful predictions than the student.Random Probing for Structural Self-Interactions in Graph Neural Networks
Graph Neural Networks (GNNs) fundamentally lack the ability to capture structural properties defined by node self-interactions, such as cycle counts, subgraph centrality, and heat kernel signatures.Lifting Finite-Sample Gaussian Approximation of Wide Neural Networks to Functional Convergence
Randomly initialised neural networks of width $m$ converge to Gaussian processes as $m \to \infty$, with two types of quantitative bounds characterising this convergence.Looped Reasoning Finishes Earlier Than You Think
Looped reasoning with dynamic depth can be viewed as relaxation toward solution attractors in a learned dynamical landscape.