Research
The long-term research goal is to build understand, evaluate, and enhance modern AI models, such as pre-trained and large foundation models. We create new theory, algorithms, applications, and open-sourced library to achieve our goal.
- Machine learning: Iām generally interested in designing algorithms and applications to make machine learning systems more robust, trustworthy, and responsible. Related topics include: machine learning with foundation models, robust machine learning, OOD / domain generalization, transfer learning, semi-supervised learning, federated learning, and related applications.
- Large language models: We mainly focus on understanding the potential and limitation of large foundation models. Related topics: LLM evaluation and enhancement.
- AI for social sciences: How to measure the impact of generative AI on different domains? How to assist interdisciplinary domains using powerful AI models? How to use existing social science knowledge to help us better understand AI behaviors?
Media Coverage
- Abstracts: NeurIPS 2024 with Jindong Wang and Steven Euijong Whang, Microsoft Research Podcast. December 2024. [Website]
- The Answer To Why Emotionally Worded Prompts Can Goose Generative AI Into Better Answers And How To Spur A Decidedly Positive Rise Out Of AI, by Forbes. November 2023. [Webpage]
- CulturePark for low-resource large language models, by MIT Technology Review. June 2024. [Webpage]
- Epic and Generative AI, by Epic. December 2024. [Webpage]
- Unveiling the Power of Semi-Supervised Learning: The Unified Semi-Supervised Learning Benchmark, by Pytorch. May 2024. [Webpage]
- EmotionPrompt in RAG, by LlamaIndex. August 2023. [Webpage]
- Exploring the effects of emotional stimuli to large language models, by TexExplore. September 2023. [Webpage]
- CompeteAI: An Artificial Intelligence AI Framework that Understands the Competition Dynamics of Large Language Model-based Agents, by Daily.dev, July 2024. [Webpage]
Funding and Grants
- Co-Principal Investigator. āMitigating Ethical AI Threats: Dynamic Benchmarks for Securing Multimodal Social Intelligence in Large Language Models(LLMs)ā. Awarded by The Commonwealth Cyber Initiative (CCI). 03/01/2025 ā 02/28/2026.