Industry Experience

• Applied Scientist II, Amazon, May 2024 - Present
  • Areas: LLM, RL, NLP, Machine Learning, Deep Learning (DL), LLM post-training (e.g., alignment, reasoning, evaluation, SFT, RL, and agentic long-horizon RL), self-improving coding&ads agents
  • Teams: AWS CodeLLM Team, Amazon Ads Foundation Model Team

Selected Industry Projects

• Large-scale synthetic data generation for LLM training and evaluation (e.g., reasoning traces, agentic tool-use benchmarks)
• LLM post-training: SFT and RL (e.g., PPO, GRPO, DAPO, GSPO, CISPO and their variants), including agentic long-horizon RL, for coding and ads agents
• Self-evolving agents for agent harness evolution and LLM post-training as an automated AI researcher
• Coding agents for large-scale code decomposition, migration, documentation, and evaluation

Education Experience

• Ph.D in Computer Science, Georgia Institute of Technology, Aug 2019 - May 2024
  • Advisors: Prof. Srijan Kumar and Prof. Mustaque Ahamad
  • Research Areas: Machine Learning, Natural Language Processing, Deep Learning, Data Science
• M.S. in Computer Science, University of Macau, Aug 2016 - Jul 2019
  • GPA: 3.9/4.0, Advisor: Prof. Lionel M. Ni, Vice President of Hong Kong University of Science and Technology-HKUST (moved from HKUST to University of Macau then back to HKUST)
• B.S. in Electronic Engineering, University of Electronic Science and Technology of China, Aug 2012 - Jul 2016
  • GPA: 3.9/4.0, Rank: 2/160

Internship Experience

• 2023.05 - 2023.08: Amazon Search, Palo Alto, California
  • Applied Scientist Intern, Search Mission Understanding Team, Amazon Search/A9.com
  • Hosts: Ms. Sreyash Nag, Dr. Limeng Cui, Dr. Zheng Li
• 2022.05 - 2022.08: Amazon Retail, San Diego, California
  • Applied Scientist Intern, Machine Learning Accelerator Team, SPS
  • Hosts: Dr. Shobeir Fakhraei, Mr. Akshay Kulkarni, Dr. Na Zhang, Dr. Chris Jones
• 2021.05 - 2021.08: Amazon Retail, San Diego, California
  • Applied Scientist Intern, Machine Learning Accelerator Team, SPS
  • Hosts: Ms. Veena Padmanabhan, Dr. Hyun Ah Song, Dr. Na Zhang, Dr. Chris Jones

Research Experience

• 2019.08 - 2024.05: Georgia Institute of Technology, Atlanta, Georgia
  • Graduate Research Assistant, School of Computer Science
  • Advisors: Prof. Srijan Kumar and Prof. Mustaque Ahamad
• 2019.01 - 2019.07: Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong
  • Graduate Research Assistant, Department of Computer Science
  • Advisors: Prof. Lei Chen
• 2016.08 - 2019.07: Hong Kong University of Science and Technology, China
  • Graduate Research Assistant, Fork Ying Tung Graduate School
  • Advisors: Prof. Lionel M. Ni and Dr. Min Gao

Selected PhD Research Projects

• Large Language Models for Controllable Text Generation via Reinforcement Learning
  • Advisors: Prof. Mustaque Ahamad and Prof. Srijan Kumar
  • Research output: ACM WWW’23 code and data
    • Design novel BERT-based reward models in offline RL framework to capture desirable textual properties in text generation
    • Implemented a transformer decoder-based GPT-kind language model for counter-misinformation generation
    • Curate high-quality misinformation-related conversational datasets and fine-tuned LLaMA2 using LoRA
• Multi-task Learning-based Personalized Text Generation for Attack/Defense
  • Advisors: Prof. Mustaque Ahamad and Prof. Srijan Kumar
  • Research output: ACM KDD’21 code and data
    • Proposed a Generative Adversarial Network (GAN)-based text generation framework for personalization and adversarial attack
    • Design a multi-stage multi-task optimization strategy to improve the generation performance
    • Leverage adversarial machine learning for fine-tuning and enhancing the model robustness
• BERT-based Fine-grained Text and Textual Sequence Classification
  • Advisors: Prof. Mustaque Ahamad and Prof. Srijan Kumar
  • Research output: IEEE BigData’20 code and data and ACM ASONAM’21 code and data
    • Implement the masked language model-enhanced fine-tuning- and feature-based BERT for misinformation and hate speech classification
    • Propose the transformer-based sequence-aware deep sequence classifier powered by data augmentation from OpenAI ChatGPT and GPT4
    • Crawl large-scale tweets and user networks, and analyze the spread of misinformation and hate speech on Twitter

Award

• Best Reviewer Award, International AAAI Conference on Web and Social Media, 2024
• Outstanding Reviewer Award, ACM Web Conference, 2024
• Best Paper Nomination Award, ACM Web Conference, 2023
• Outstanding Bachelor Graduate Student, University of Electronic Science and Technology of China, 2016
• National Scholarship (for top 1%), Ministry of Education of China, 2013 and 2014