Yunhao Yang is a Ph.D. student in computer science at The University of Texas at Austin. He started his Ph.D. program in Fall 2022. Prior to this, he received B.S. and M.S. degrees in computer science, and a B.A. in mathematics from UT Austin. He is currently a member of the Center for Autonomy, supervised by Prof. Ufuk Topcu. His research interests include integrating foundation models and formal methods for autonomy, AI safety, and privacy.
yunhaoyang234@gmail.com
Department of Computer Science
The University of Texas at Austin
Austin, Texas
USA
Publications
* Equal Contribution
1 All accepted papers get oral presentation
Journal Publication
Yunhao Yang*, Parham Gohari* and Ufuk Topcu. On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning
Proceedings on Privacy Enhancing Technologies 2023.
Yunhao Yang, Zhaokun Xue and Andrew Whinston. Self-Enhancing Multi-filter Sequence-to-Sequence Model
Procedia Computer Science, Elsevier, 2023.
Conference Proceeding
Yunhao Yang*, Neel Bhatt*, Tyler Ingebrand*, William Ward, Steven Carr, Zhangyang Wang and Ufuk Topcu. Fine-Tuning Language Models Using Formal Methods Feedback: A Use Case in Autonomous Systems
Annual Conference on Machine Learning and Systems (MLSys) 2024. Oral Presentation1
Yunhao Yang, Cyrus Neary and Ufuk Topcu. Multimodal Pretrained Models for Verifiable Sequential Decision-Making: Planning, Grounding, and Perception
International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) 2024. Oral Presentation1
Yunhao Yang and Andrew B Whinston. A Survey on Reinforcement Learning for Combinatorial Optimization
IEEE World Conference on Applied Intelligence and Computing (AIC) 2023.
Yunhao Yang, Yi Wang, Chandrajit Bajaj. Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing
IEEE World Conference on Applied Intelligence and Computing (AIC) 2023. Best Paper Award
Yunhao Yang and Zhaokun Xue. Training Heterogeneous Features in Sequence to Sequence Tasks: Latent Enhanced Multi-filter Seq2Seq Model
Proceedings of Intelligent Systems Conference (IntelliSys) 2022. Lecture Notes in Networks and Systems, Springer. Best Student Paper Award
Patent
Ufuk Topcu, Yunhao Yang, Cyrus Neary, and Jean-Raphaël Gaglione. Automaton-Based Controller and Method with Generative Language Models for Task Execution
US Patent Application No.63/602,380.
Community Services
Journal and Conference Review
Program Committee for CSCT 2024, CSCT 2023, CSCT 2023, ICCIS 2023, ICIVC 2023
Reviewer for Journal of Computational and Cognitive Engineering, FMDM@NeurIPS 2023, NeurIPS 2022, LLMAgents@ICLR 2024
Volunteer
STEM Girl Day at UT Austin, 2024
Mentor for REACT RUE summer program, 2023
Volunteer for LASA High School Visit, 2023
Volunteer for FIRST Technical Challenge: Texas-Central GEMS League Tournament, 2023
Volunteer for TACC Back@TACC, 2022