SafePro: Evaluating the Safety of Professional-Level AI Agents
ICLR Workshop on Agents in the Wild: Safety, Security, and Beyond, 2026
I'm a Master's student in the Machine Learning Department at Carnegie Mellon University. Previously, I was a Computer Science undergrad at UC Santa Cruz, where I published research with multiple labs (ERIC Lab, Tech4Good Lab, and more).
My current interests revolve around generative and world modeling, embodied intelligence, AI safety, and controllable AI systems. I frequently work with other researchers (NVIDIA, Yale University, University of Michigan, UC Santa Barbara) and am always open to new ideas; please reach out if you are interested in collaborating!
In addition to research, I've done a lot of engineering work, including internships at Google and Amazon.
Research
* denotes equal contribution
Bringing ‘On-the-Job’ Learning into Education: Lessons From a Micro-Role Apprenticeship Program and Implications for Platform Design
ACM CHI Conference on Human Factors in Computing Systems (Poster), 2026
Designing Virtual Reality Games About Grief: Reflections from Psychology and Healthcare Professionals
Digital Games Research Association (DiGRA) Conference, 2026
PhyWorldBench: A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
International Conference on Learning Representations (ICLR), 2026 Oral
The Name-Free Gap: Policy-Aware Stylistic Control in Music Generation
NeurIPS Workshop on Artificial Intelligence for Music: Where Creativity Meets Computation, 2025
CCC: Enhancing Video Generation via Structured MLLM Feedback
ICML Workshop on Test-Time Adaptation: Putting Updates to the Test, 2025
Self-Resource Allocation in Multi-Agent LLM Systems
ICML Workshop on Multi-Agent Systems in the Era of Foundation Models, 2025
Human-centered World Modeling: Enhancing Multi-Agent AI Adaptability with Chain-of-Thought and Symbolic Reasoning
CHI Workshop on Human-AI Interaction for Augmented Reasoning, 2025 Oral