arXiv subjects

Danping Liu

Publications and source records attributed to Danping Liu.

4 recordsLinked to original sources

arXiv2026

JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

JD$.$com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchants, with a catalog of tens of billions of SKUs. At this scale, high-quality, structured item knowledge underpins a better consumer experience, lower management costs, and higher operational efficiency-yet producing and serving it poses three industrial-scale challenges: fast-emerging concepts, high-quality knowledge production for massive SKUs, and diverse downstream requirements. To address these challenges, we present the JD Oxygen AI Item Center (Oxygen AIIC), an industrial-scale platform built on LLMs/VLMs for item-knowledge production and service. Oxygen AIIC is built around four core pillars: (i) ontology engineering driven by efficient human-AI collaboration, which supports the dynamic evolution and agile expansion of an ontology with millions of entries; (ii) a "Semantic Search then Discrimination"(S2D) knowledge identification architecture that, combined with throughput improvement strategies, enables scalable, extensible, and high-throughput AI Item Library production for tens of billions of SKUs; (iii) self-evolving item-understanding LLMs/VLMs that improve in a stable and controllable manner, enabling knowledge production with 94.2% precision and 82.8% recall; and (iv) a unified item tunnel that serves as the data and service hub. Oxygen AIIC now covers tens of thousands of JD categories and processes hundreds of millions of item updates per day on Huawei Ascend NPUs. It has accumulated hundreds of billions of item-knowledge assets. Deployed across core business scenarios-including search, recommendation, operations, category planning-Oxygen AIIC has delivered measurable gains at scale. Search-traffic coverage reaches 80.4%, item-information quality issues drop by 37%, the automated fill rate of core attributes during item listing exceeds 80%.

cs.AI↗

arXiv2023

A Likelihood Approach to Incorporating Self-Report Data in HIV Recency Classification

Estimating new HIV infections is significant yet challenging due to the difficulty in distinguishing between recent and long-term infections. We demonstrate that HIV recency status (recent v.s. long-term) could be determined from the combination of self-report testing history and biomarkers, which are increasingly available in bio-behavioral surveys. HIV recency status is partially observed, given the self-report testing history. For example, people who tested positive for HIV over one year ago should have a long-term infection. Based on the nationally representative samples collected by the Population-based HIV Impact Assessment (PHIA) Project, we propose a likelihood-based probabilistic model for HIV recency classification. The model incorporates both labeled and unlabeled data and integrates the mechanism of how HIV recency status depends on biomarkers and the mechanism of how HIV recency status, together with the self-report time of the most recent HIV test, impacts the test results, via a set of logistic regression models. We compare our method to logistic regression and the binary classification tree (current practice) on Malawi, Zimbabwe, and Zambia PHIA data, as well as on simulated data. Our model obtains more efficient and less biased parameter estimates and is relatively robust to potential reporting error and model misspecification.

stat.AP↗

arXiv2019

Statistical approaches using longitudinal biomarkers for disease early detection: A comparison of methodologies

Early detection of clinical outcomes such as cancer may be predicted based on longitudinal biomarker measurements. Tracking longitudinal biomarkers as a way to identify early disease onset may help to reduce mortality from diseases like ovarian cancer that are more treatable if detected early. Two general frameworks for disease risk prediction, the shared random effects model (SREM) and the pattern mixture model (PMM) could be used to assess longitudinal biomarkers on disease early detection. In this paper, we studied the predictive performances of SREM and PMM on disease early detection through an application to ovarian cancer, where early detection using the risk of ovarian cancer algorithm (ROCA) has been evaluated. Comparisons of the above three methods were performed via the analyses of the ovarian cancer data from the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial and extensive simulation studies. The time-dependent receiving operating characteristic (ROC) curve and its area (AUC) were used to evaluate the prediction accuracy. The out-of-sample predictive performance was calculated using leave-one-out cross-validation (LOOCV), aiming to minimize the problem of model over-fitting. A careful analysis of the use of the biomarker cancer antigen 125 for ovarian cancer early detection showed improved performance of PMM as compared with SREM and ROCA. More generally, simulation studies showed that PMM outperforms ROCA unless biomarkers are taken at very frequent screening settings.

stat.AP↗

arXiv2015

Mixed model and estimating equation approaches for zero inflation in clustered binary response data with application to a dating violence study

The NEXT Generation Health study investigates the dating violence of adolescents using a survey questionnaire. Each student is asked to affirm or deny multiple instances of violence in his/her dating relationship. There is, however, evidence suggesting that students not in a relationship responded to the survey, resulting in excessive zeros in the responses. This paper proposes likelihood-based and estimating equation approaches to analyze the zero-inflated clustered binary response data. We adopt a mixed model method to account for the cluster effect, and the model parameters are estimated using a maximum-likelihood (ML) approach that requires a Gaussian-Hermite quadrature (GHQ) approximation for implementation. Since an incorrect assumption on the random effects distribution may bias the results, we construct generalized estimating equations (GEE) that do not require the correct specification of within-cluster correlation. In a series of simulation studies, we examine the performance of ML and GEE methods in terms of their bias, efficiency and robustness. We illustrate the importance of properly accounting for this zero inflation by reanalyzing the NEXT data where this issue has previously been ignored.

stat.AP↗