| layout | about | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| title | About | ||||||||
| permalink | / | ||||||||
| profile |
|
||||||||
| news | true | ||||||||
| selected_papers | true | ||||||||
| social | true |
Hi! I'm Keyu He, a Master's in NLP @ Carnegie Mellon University SCS. Previously, I earned my B.S. from the University of Southern California, where I double‑majored in Computer Science and Applied & Computational Mathematics.
I am passionate about socially intelligent AI agents that can reason about people, interact naturally, and support human learning. At CMU, I'm researching socially intelligent AI with Professor Maarten Sap, and human-centered AI evaluation with Professor Sherry Tongshuang Wu. Previously at USC, I conducted NLP research in the INK Lab and DILL Lab under Professors Xiang Ren and Swabha Swayamdipta.
- USC Center for Undergraduate Research in Viterbi Engineering (CURVE) fellow.
- Fellowship awarded multiple times (Spring 2024 -- Spring 2025), with a total funding amount of $6,750.
- USC Academic Achievement Award: Fall 2022 - Fall 2024.
- This award covered 11 units of tuition costs in total, amounting to approximately $24,000.
- USC Dornsife Dean’s List & USC Viterbi Dean's List: 2021-2025.
- 4th Place, USC Integral Bee Competition: 2022.
- Socially Intelligent AI: Developing methods to find and generate datasets of AI social scenarios with verifiable rewards, then applying reinforcement learning to train models that improve their social interaction abilities.
- Human-Centered AI Evaluation: Creating AI-powered tools and assessment methods to evaluate users' prompt engineering skills and proficiency in "vibe programming" with large language models.
As a Course Producer and grader for multiple computer science and math courses, I’ve mentored peers and fostered inclusive learning environments.
Outside academics, I’ve led teams in competitions like the Kaggle LLM-Prompt-Recovery Challenge, earning a top-3.4% ranking globally.