[{"content":" Top 3 / 859 teams — E.SUN AI Open Competition, Winter 2021 (Credit-Card Category Recommendation). Final NDCG@3 = 0.726037 (Top-1 = 0.727069). Oct 2021 – Feb 2022 Top 1 / 401 teams — Chunghwa Post Big Data Competition 2019. Proposed an ML-integrated system with an estimated 65% reduction in failed deliveries. Apr – Jun 2019 NCKU Outstanding Talents Scholarship 2021 (Bank SinoPac). Nov 2021 Excellent Award, Statistics Certificate — Chinese Applied Statistics Association. May 2019 Advanced Award, Competition of Statistics — NCKU. May 2017 ","permalink":"https://jayenliao.github.io/awards/","summary":"\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003eTop 3 / 859 teams\u003c/strong\u003e — E.SUN AI Open Competition, Winter 2021 (Credit-Card Category Recommendation). Final NDCG@3 = 0.726037 (Top-1 = 0.727069). \u003cem\u003eOct 2021 – Feb 2022\u003c/em\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eTop 1 / 401 teams\u003c/strong\u003e — Chunghwa Post Big Data Competition 2019. Proposed an ML-integrated system with an estimated \u003cstrong\u003e65%\u003c/strong\u003e reduction in failed deliveries. \u003cem\u003eApr – Jun 2019\u003c/em\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eNCKU Outstanding Talents Scholarship 2021\u003c/strong\u003e (Bank SinoPac). \u003cem\u003eNov 2021\u003c/em\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eExcellent Award, Statistics Certificate\u003c/strong\u003e — Chinese Applied Statistics Association. \u003cem\u003eMay 2019\u003c/em\u003e\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003eAdvanced Award, Competition of Statistics\u003c/strong\u003e — NCKU. \u003cem\u003eMay 2017\u003c/em\u003e\u003c/li\u003e\n\u003c/ul\u003e","title":"Awards"},{"content":"† denotes co-first authorship.\nALICE: A Multifaceted Evaluation Framework of Large Audio-Language Models\u0026rsquo; In-Context Learning Ability Yen-Ting Piao†, Jay Chiehen Liao†, Wei-Tang Chien†, Toshiki Ogimoto†, Shang-Tse Chen, Yun-Nung Chen, Chun-Yi Lee, Shao-Yuan Lo. arXiv preprint, 2026. [arXiv]\nA three-stage framework that progressively reduces textual guidance to evaluate LALMs\u0026rsquo; in-context learning under audio conditioning. Built the LALM inference framework; ran experiments; led results analysis. TabGSL: Graph Structure Learning for Tabular Data Prediction Jay Chiehen Liao, Cheng-Te Li. IEEE International Conference on Big Data (BigData), 2025. [IEEE Xplore] · [arXiv]\nA contrastive-learning GNN with a transformer-based extractor that jointly learns instance correlations and feature interactions for tabular prediction. Outlined a hyperparameter-tuning guide for graph structure learning. Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions Cheng-Te Li, Yu-Che Tsai, Chih-Yao Chen, Jay Chiehen Liao. ACM Computing Surveys, 2025. [ACM] · [arXiv] · [GitHub]\nSystematic review of GNNs designed and implemented for tabular data learning. Presented as tutorials at IEEE ICDE 2023 and The Web Conference (WWW) 2023. Enhancing PrEP Adherence Through Person-Centred Mobile App Interventions: A Real-World Data and Machine Learning Approach Using UPrEPU Among Gay, Bisexual and Other Men Who Have Sex with Men in Taiwan Jay Chiehen Liao, Huei-Jiuan Wu, Tsan-Tse Chuang, Tsai-Wei Chen, Carol Strong. Journal of the International AIDS Society, 28(S5), 2025. [paper]\nLeveraged real-world mobile-app logs and user attributes to predict PrEP-protected sexual events among GBMSM, with SHAP-based analysis of adherence factors. Predictive Modeling for 14-Day Unplanned Hospital Readmission Risk by Using Machine Learning Algorithms Yu-Tai Lo†, Jay Chiehen Liao†, Mei-Hua Chen, Chia-Ming Chang, Cheng-Te Li. BMC Medical Informatics and Decision Making, 21, 2021. [paper]\nAn explainable ML model for 14-day unplanned hospital-readmission risk from EHR data of 24k+ patients, with SHAP-based feature analysis aligned with clinical experience. ","permalink":"https://jayenliao.github.io/publications/","summary":"\u003cp\u003e† denotes co-first authorship.\u003c/p\u003e\n\u003ch3 id=\"alice-a-multifaceted-evaluation-framework-of-large-audio-language-models-in-context-learning-ability\"\u003eALICE: A Multifaceted Evaluation Framework of Large Audio-Language Models\u0026rsquo; In-Context Learning Ability\u003c/h3\u003e\n\u003cp\u003eYen-Ting Piao†, \u003cstrong\u003eJay Chiehen Liao\u003c/strong\u003e†, Wei-Tang Chien†, Toshiki Ogimoto†, Shang-Tse Chen, Yun-Nung Chen, Chun-Yi Lee, Shao-Yuan Lo. \u003cem\u003earXiv preprint, 2026.\u003c/em\u003e \u003ca href=\"https://arxiv.org/abs/2603.20433\"\u003e[arXiv]\u003c/a\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eA three-stage framework that progressively reduces textual guidance to evaluate LALMs\u0026rsquo; in-context learning under audio conditioning.\u003c/li\u003e\n\u003cli\u003eBuilt the LALM inference framework; ran experiments; led results analysis.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"tabgsl-graph-structure-learning-for-tabular-data-prediction\"\u003eTabGSL: Graph Structure Learning for Tabular Data Prediction\u003c/h3\u003e\n\u003cp\u003e\u003cstrong\u003eJay Chiehen Liao\u003c/strong\u003e, Cheng-Te Li. \u003cem\u003eIEEE International Conference on Big Data (BigData), 2025.\u003c/em\u003e \u003ca href=\"https://ieeexplore.ieee.org/abstract/document/11402569\"\u003e[IEEE Xplore]\u003c/a\u003e · \u003ca href=\"https://arxiv.org/abs/2305.15843\"\u003e[arXiv]\u003c/a\u003e\u003c/p\u003e","title":"Publications"}]