- One paper on mitigating reward hacking is accepted @ NeurIPS 2025
- Our KDD@2025 paper is selected as the Best Paper Award (Research Track)
- One paper is accepted @ KDD 2025
- One paper is accepted @ ICML 2025
- One paper is accepted @ IJCAI 2025
- One paper on benchmarking spurious biases in Multimodal LLMs is accepted @ NeurIPS 2024’s Workshop on Responsibly Building the Next Generation of Multimodal Foundational Models
- One paper is published @ NAR Genomics and Bioinformatics
- One paper is accepted @ ECCV 2024
- One paper is accepted @ KDD 2024
- One paper is accepted @ IJCAI 2024
- One paper is accepted @ AAAI 2024
Research Experience
- Advanced AI Research Scientist, Accenture, June 2025 - Present
- AI Research Scientist, Accenture, June 2025
Education
- Ph.D. in Computer Science, University of Virginia, advised by Prof. Aidong Zhang
- Master's degree, University of Science and Technology of China
- Bachelor's degree, Sun Yat-sen University
Background
Research Interests: Artificial Intelligence and Machine Learning, with a main research theme on AI alignment and safety from the perspective of detecting and mitigating spurious correlations. Specific topics include shortcut learning in image/text classification, superficial learning in multimodal models, reward hacking in reinforcement learning, benchmarking superficial learning in AI models, and robust reasoning and planning in agentic systems. Additionally, passionate about application-driven machine learning, leveraging techniques such as self-supervised learning and generative modeling to accelerate knowledge discovery in genomics.