Skip to content
Full feed

Feed 28,363 posts

Every story across every category, newest first. Each card links to the original publisher; daily-brief posts open as editorial pages.

arXiv stat.ML Papers

Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP

arXiv:2608.00989v1 Announce Type: new Abstract: Most FDR-controlled feature selection methods are designed for coordinate-wise hypotheses, where each feature has a single weight or importance score. This…

arXiv stat.ML Papers

How fine a change can moments see? A scale law for detecting distribution shift, with a kernel calibration rule

arXiv:2608.01268v1 Announce Type: new Abstract: Detecting that a stream of high-dimensional embeddings has changed is usually framed as a choice of statistic. We give a scale…

arXiv stat.ML Papers

Finite-Probe Total-Variation Certificates for Finite-Basis Drifting Models

arXiv:2608.01547v1 Announce Type: new Abstract: Drifting objectives compare a target and model distribution through a vector field observed noisily at finitely many locations. We ask what…

arXiv stat.ML Papers

Dominant Arm Identification with Mixing and Recycling Observed Samples

arXiv:2608.01545v1 Announce Type: new Abstract: We study the problem of identifying the dominant arm in multi-armed bandits, where the objective is to find the action with…

arXiv stat.ML Papers

Benign Overfitting in Linear Classifiers with a Bias Term

arXiv:2511.12840v2 Announce Type: replace Abstract: Overparameterized models often generalize well even when they interpolate noisy training data. This is known as benign overfitting. For linear classification,…

arXiv stat.ML Papers

The Label Defines the Timescale: Trait-State Limits of Temporal-Aggregate Learning

arXiv:2608.01587v1 Announce Type: new Abstract: Machine-learning benchmarks often pair a label that aggregates a long temporal horizon with input observed through one or a few short…

arXiv stat.ML Papers

Tail-Aware Information-Theoretic Bounds for LLM Alignment under Heavy-Tailed Rewards

arXiv:2604.10727v2 Announce Type: replace Abstract: Classical information-theoretic learning bounds typically rely on KL mutual information and moment-generating-function (MGF) arguments, which are well matched to bounded or…

arXiv stat.ML Papers

A probabilistic framework for irreversible kinetics

arXiv:2601.10763v2 Announce Type: replace-cross Abstract: A probabilistic framework for irreversible kinetics is proposed in which a constrained path functional $mathcal J$ encodes constitutive physics and observations…

arXiv stat.ML Papers

Sampling Decisions: Exact Path-Space Control for Physics-Informed Generative Sampling

arXiv:2503.14549v4 Announce Type: replace-cross Abstract: Scientific generative models must turn tractable local decisions into globally correlated samples that respect physical constraints. We introduce Sampling Decisions, a…

arXiv stat.ML Papers

Causal Inference with Unstructured Treatments

arXiv:2608.00657v1 Announce Type: new Abstract: Causal inference usually concerns a scalar treatment, yet in many problems the treatment is unstructured: a text, an image, or a…

arXiv stat.ML Papers

Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditions

arXiv:2605.24590v2 Announce Type: replace-cross Abstract: Low-light, long-exposure defocus deblurring remains a challenging problem due to the simultaneous presence of severe blur and complex biased noise. Existing…

arXiv cs.NE Papers

SDDMO-Bench: A Benchmark Suite for Streaming Data-Driven Dynamic Multi-Objective Optimization

arXiv:2608.00474v1 Announce Type: new Abstract: Streaming data-driven dynamic multi-objective optimization requires algorithms to track time-varying Pareto fronts using only sequential observations under concept drift. However, systematic…

arXiv cs.NE Papers

ChaosProbe: A Neurochaotic Lens on Frozen Transformer Input-Embedding Spaces

arXiv:2608.01968v1 Announce Type: cross Abstract: Transformer models are most often understood through what they do: their benchmark performance, generation quality, or behavior on downstream tasks. Yet…

arXiv cs.NE Papers

Spike-HTR: Spiking Neural Transformer for Handwritten Text Recognition

arXiv:2608.01646v1 Announce Type: new Abstract: Handwritten Text Recognition (HTR) is computationally imbalanced in two ways: most image pixels are background, and many width-axis sequence positions are…

arXiv cs.NE Papers

An Evolutionary Algorithm Assisted by an Ensemble of Pareto-Optimal Surrogate Models

arXiv:2608.01777v1 Announce Type: new Abstract: An ensemble of surrogate models helps improve the prediction quality and robustness of surrogate models, and in turn, the search performance…

arXiv cs.NE Papers

Towards Autonomous Formulaic Alpha Discovery: An Evolutionary Computation Perspective

arXiv:2608.01789v1 Announce Type: new Abstract: Automated formulaic alpha discovery aims to generate predictive and interpretable trading signals from large symbolic factor spaces. Its effectiveness is constrained…

arXiv cs.NE Papers

Unsupervised Multidomain Approaches to Named Entity Recognition with Small Datasets

arXiv:2608.00984v1 Announce Type: cross Abstract: This paper explores the challenges and the methodologies associated with learning quality representations in scenarios with unlabelled small or limited datasets…

arXiv cs.NE Papers

DGA$_2$D: Directed Graph-Guided Automated Algorithm Design with Large Language Models

arXiv:2608.00700v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has opened new avenues for Automated Heuristic Design (AHD) for solving NP-hard combinatorial…

arXiv cs.NE Papers

SMM Transformer: Leveraging Spiking Neural Networks for Multimodal Tasks

arXiv:2608.01622v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) enable event-driven computation with sparse activations, but building multimodal Transformers on SNNs is hindered by unstable training…

arXiv cs.NE Papers

Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory

arXiv:2608.01947v1 Announce Type: cross Abstract: The ability to robustly maintain and update continuous variables is a hallmark of working memory. While classical continuous attractor networks suffer…

arXiv cs.NE Papers

Directing Open-Ended Evolution in Artificial Life via Multi-Scale Path Divergence

arXiv:2606.17091v2 Announce Type: replace Abstract: Open-ended evolution (OEE) in artificial life is typically driven by uninterpretable, black-box neural-network complexity metrics, leaving life-like systems disconnected from physical…

arXiv cs.NE Papers

Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts

arXiv:2605.30359v2 Announce Type: replace Abstract: Generating high-performance GPU kernels remains challenging due to the need for both correctness and hardware-aware optimization. While large language models (LLMs)…

arXiv cs.NE Papers

Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models

arXiv:2506.07121v2 Announce Type: replace-cross Abstract: Ensuring the safety and robustness of large language models (LLMs) is a fundamental challenge and a critical prerequisite for the responsible…

arXiv cs.NE Papers

The DNA of Calabi-Yau Hypersurfaces

arXiv:2405.08871v4 Announce Type: replace-cross Abstract: We implement Genetic Algorithms for triangulations of four-dimensional reflexive polytopes which induce Calabi-Yau threefold hypersurfaces via Batyrev's construction. We demonstrate that…