AI & Machine Learning · Computer Science & AI
Machine Learning (Statistics)
The newest papers in Machine Learning (Statistics) that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
1,749 papers, from 4 September 2026 to 5 November 2026: 1,749 arXiv preprints.
Get the few papers worth your time in Machine Learning (Statistics) every morning.
Follow Machine Learning (Statistics) 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 58
Learning Global Sensitivity Indices from Observational Data: A Metamodel-Based Approach
Classical variance-based Global Sensitivity Analysis (GSA) assumes that the input--output mechanism can be repeatedly evaluated under a designed sampling scheme, which is infeasible when only a…M$^2$Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecasting
Station weather forecasting is fundamentally shaped by both complex spatial dependencies across stations and strong physical coupling among weather variables.STCFormer: Adaptive Spatio-Temporal Modeling with Dynamic Cluster Transformer for Station-based Weather Forecasting
Station-based weather forecasting supports daily life and economic activity, yet accurate forecasts require modeling complex spatial dependencies among stations.FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training
Replay selectors often rank cached trajectories by format feedback, confidence, freshness, or response length, although cache-level correctness and downstream learner utility are distinct objectives.MatrixReward: Reward from Rubric Matrix for Open-Ended Generation
Open-ended query generation lacks standard answers, thus necessitating an effective reward mechanism.RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting
Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series inference is ill-suited to neighbor-rich forecasting, where each query has access to related but…VANDAM: Viewing a nucleotide sequence with DNA molecular priors
Contemporary Genomic Foundation Models (GFMs) rely on a DNA-as-a-string paradigm that employs masked token prediction objectives for pretraining.Transferable Graph Metanetworks
A weight space network (or metanetwork) takes the weights of another neural network as input and predicts properties of it.Learning to Cover Locally: Graph Neural Combinatorial Optimization under a Hard Information Horizon
Neural combinatorial optimization typically assumes a centralized solver that reads the whole instance.Target-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Model
Knowing how much a causal predictor could improve need not reveal the gain of the repair actually learned.IrekoGPT: Turning Structured Pruning into Post-Hoc Slimmable LLMs
We introduce IrekoGPT, a post-hoc method for converting pretrained LLMs into slimmable models whose width can be adjusted at inference time.ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs
Continual parameter-efficient fine-tuning for large language models (LLMs) must balance retention of previously acquired knowledge, adaptation to new tasks, and strict parameter budgets.Exact information accounting for SGD methods
As an alternative to the standard geometric analyses, we give an exact, information-theoretic analysis of stochastic gradient descent (SGD) and its variants.Heteroskedastic Canonical Polyadic Tensor Decomposition
When minimizing the squared-error loss, the popular CP decomposition can be interpreted as parameter inference in a Gaussian model with a low-rank mean tensor and constant variance across the tensor…Fractional Laplace Neural Operators: Exact Architectures, an Expressivity Frontier at Criticality, and Certified Stability for Memory-Driven Network Dynamics
Neural operators learn maps between function spaces, while hereditary network dynamics are described by Volterra resolvents with non-rational Laplace symbols.Adaptive Conformal Prediction for Image Regression Models with Application to an Inertial Confinement Fusion Emulator
Uncertainty quantification is critical in scientific machine learning, where black-box, image-based models are increasingly deployed in high-stakes settings.Grand Canonical Generators
We introduce Grand Canonical Generators (GCG), a generative framework that extends Boltzmann generators to the grand canonical ensemble.How Divergence Becomes Decision Flips in Compressed Language Models
Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on the dense model's outputs needs to know how many…Multifidelity Formulations for Triangular Transport
We develop multifidelity methods for constructing triangular transport maps from samples, when high-fidelity data are scarce but lower-fidelity data are more abundant.Sequential Functional Structured Tucker Compression for Large Language Model Attentions
Post-training compression of LLM attention is often formulated as independent matrix approximation, ignoring both the shared structure among attention projections and the representation shift…