I am a senior applied scientist at Amazon in Seattle. My first name “Zhiyu” comes from an ancient Chinese poem (好雨知时节), meaning good rain knows the best time to fall. I received my PhD from Lehigh University in 2022, advised by Prof. Brian D. Davison. My research interests lie in natural language processing and information retrieval, with a focus on foundation large language models (LLMs).
About
Education
Ph.D. in Computer Science
Lehigh University, Bethlehem, PA, USA
2015 – 2022 · GPA 3.97/4.0
Exchange Program
École Supérieure d'Ingénieurs Léonard de Vinci, Paris, France
2014 – 2015 · GPA 15.75/20
B.E. in Computer Science
Nanjing University of Aeronautics and Astronautics, Nanjing, China
2011 – 2015 · GPA 4.2/5.0 (rank 1/94)
Experience
Applied Scientist Intern
Amazon · Seattle, WA, US (remote)
May 2021 – Sep 2021
- Proposed a reinforcement learning method for conversational question answering, accepted by EMNLP Industry Track 2022.
- Mentors / Managers: Jie Zhao, Anjie Fang, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi.
Applied Science Intern
Zhuiyi Technology · Shenzhen, Guangdong, China
May 2019 – Sep 2019
- Led a team solving SuperGLUE benchmark tasks, achieving a 2nd-place ranking, covered in China Daily (中国日报) and Sina Tech (新浪科技).
- Manager: Yinan Xu.
Applied Science Intern
Bloomberg · Princeton, NJ, USA
Jun 2016 – Aug 2016
- Analysis of Bloomberg Data License usage patterns.
- Manager: Michael Liebman.
Publications
Efficient Low-Rank Index Routing for High-Dimensional Approximate Nearest Neighbor Search
Dependency Relationships-Enhanced Attentive Group Recommendation in HINs
LLM-based Dialogue Labeling for Multiturn Adaptive RAG
REIC: RAG-Enhanced Intent Classification at Scale
Wizard of Shopping: Target-Oriented E-commerce Dialogue Generation with Decision Tree Branching
Approximate Vector Set Search: A Bio-Inspired Approach for High-Dimensional Spaces
Joinable Search Over Multi-Source Spatial Datasets: Overlap, Coverage, and Efficiency
Identifying High Consideration E-Commerce Search Queries
Unbiased Learning-to-Rank Needs Unconfounded Propensity Estimation
Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data
Training-free Optimization of Generative Recommender Systems using Large Language Model Optimizers
InstructPTS: Instruction-Tuning LLMs for Product Title Summarization
Multi-Coner V2: A Large Multilingual Dataset for Fine-grained and Noisy Named Entity Recognition
Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product Search
Answering Unanswered Questions through Semantic Reformulations in Spoken QA
Model-based Unbiased Learning to Rank
Reinforced Question Rewriting for Conversational Question Answering
StruBERT: Structure-aware BERT for Table Search and Matching
MGNETS: Multi-Graph Neural Networks for Table Search
Neural Ranking Models for Document Retrieval
WTR: A Test Collection for Web Table Retrieval
A Hybrid Deep Model for Learning to Rank Data Tables
Relational Graph Embeddings for Table Retrieval
Towards Knowledge Acquisition of Metadata on AI Progress
Table Search Using a Deep Contextualized Language Model
Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification
Leveraging Schema Labels to Enhance Dataset Search
Generating Schema Labels through Dataset Content Analysis
Services
Area Chair
ACL ARR 2023, 2025
Program Committee / Reviewer
Honors & Awards
- 2021ACM SIGIR Student Travel Grant
- 2021Rossin Professional Development Program Award, Lehigh University
- 2020ISWC Student Grant
- 2020ACM SIGIR Student Travel Grant
- 2018Best Paper Award — Intl. Workshop on Profiles & Data:Search ’18
- 2018ACM SIGIR Student Travel Grant
- 2015RCEAS Dean’s Fellowship
- 2014Chinese Government Scholarship, China Scholarship Council
- 2013First Prize, National Mathematical Contest in Modeling (Jiangsu)
- 2012Honorable Mention for Social Practice
- 20122nd Prize, 11th Higher Mathematics Competition of Jiangsu Province
- 2011–14Student Scholarship
- 2011–14Merit Student
Hobbies
Coffee
I make coffee every day.
Close-up Magic
Favorite magicians: Richard Turner & Lennart Green.
Photography
Capturing moments.