Scholar
Zizhao Wang
Google Scholar ID: V4KQIWsAAAAJ
UT Austin
Citations & Impact
Citations
530
H-index
11
i10-index
14
Publications
20
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- 1. Adversarial Reinforcement Learning for Large Language Model Agent Safety
- 2. Dyn-O: Building Structured World Models with Object-Centric Representations
- 3. SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions
- 4. CaMP: Causal Motion Predictor for Robust Trajectory Forecasting
- 5. Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
- 6. Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning
- 7. ELDEN: Exploration via Local Dependencies
- 8. Learning to Correct Mistakes: Backjumping in Long-Horizon Task and Motion Planning
- 9. Causal Dynamics Learning for Task-Independent State Abstraction
Research Experience
- Spent time as a research intern at Google, Microsoft, and Honda Research Institute.
Education
- 1. PhD student in ECE at the University of Texas at Austin, advised by Prof. Peter Stone
- 2. M.S. in CS at Columbia University, advised by Prof. Peter Allen and Prof. Itsik Pe’er
- 3. Undergraduate studies at the University of Michigan - Ann Arbor
Background
- Research interests include reinforcement learning, LLM (agents), world models, and causal reasoning.
