Institution profile

Louisiana State University

Academic institutionnorthamerica · us
Official website
Research library174linked papers
Opportunities0open roles
Selected work

Representative Papers

COMBOOD: A Semiparametric Approach for Detecting Out-of-distribution Data for Image Classification

Feb 04, 2026SDM

This work addresses the challenge of effectively detecting near-distribution out-of-distribution (near-OOD) samples in image classification inference, a task where existing methods often fall short. To this end, the authors propose COMBOOD, an unsupervised semi-parametric framework that uniquely integrates non-parametric nearest-neighbor distances with parametric Mahalanobis distances in the feature embedding space to produce a unified confidence score. This fusion enables robust performance across both near-OOD and far-OOD scenarios. COMBOOD is compatible with diverse feature extractors and exhibits computational complexity that scales linearly with the embedding dimensionality. Extensive evaluations on OpenOOD v1/v1.5 benchmarks and document datasets demonstrate that COMBOOD consistently outperforms current state-of-the-art methods, with most improvements achieving statistical significance.

8 citations1 influentialRead paper

A Large-Scale Study on the Development and Issues of Multi-Agent AI Systems

Jan 12, 2026arXiv.org

This study addresses the lack of systematic understanding regarding the evolutionary dynamics of multi-agent AI systems in real-world development and maintenance. Conducting the first large-scale empirical analysis of eight prominent open-source multi-agent systems, the work examines 42,000 code commits and over 4,700 resolved issues through repository mining, commit categorization, issue tracking, and statistical modeling. It characterizes three distinct development profiles—sustained, stable, and bursty—and quantifies the distribution of maintenance activities while identifying three core issue categories: coordination, infrastructure, and defects. The findings reveal that 40.8% of commits correspond to feature enhancements, 22% of issues are defects, and 10% pertain to coordination challenges, with median resolution times ranging from under one day to two weeks, indicating an active yet fragile maintenance ecosystem.

1 citationsRead paper

The First and Second Order Asymptotics of Covert Communication over AWGN Channels

May 29, 2023arXiv.org

This work investigates the asymptotic covert capacity over an additive white Gaussian noise (AWGN) channel under a KL-divergence covertness constraint δ. For n channel uses, it establishes— for the first time—the exact first- and second-order asymptotics: the first-order term is √(nδ ln e), and the second-order term is (nδ)^(1/4)(ln e)^(3/4)√2·Q⁻¹(ε). Methodologically, it introduces a novel information-geometric quasi-ε-neighborhood construction, extending the one-dimensional Gaussian minimum-KL result to n dimensions; this is combined with truncated Gaussian coding, refined KL-divergence analysis, and second-moment-constrained power optimization to achieve the optimal power scaling law. Crucially, the theoretical analysis derives, for the first time, an explicit link between the average power upper bound and the covertness parameter δ. The results establish the fundamental second-order asymptotic covert capacity benchmark for AWGN channels.

1 citationsRead paper
Recent publications

Latest Papers