Scholar
David Huang
Google Scholar ID: e0IRutEAAAAJ
Princeton University
Citations & Impact
Citations
28
H-index
3
i10-index
0
Publications
5
Co-authors
15
list available
Publications
Resume (English only)
Academic Achievements
- 1. ICML 2025 paper acceptance - 'Improving LLM Safety Alignment with Dual-Objective Optimization' (Poster). 2. ICRA 2025 Best Paper Award Finalist - 'Robo-DM: Data Management For Large Robot Datasets'. 3. ArXiv release + open-sourcing - 'Measuring General Intelligence with Generated Games' (GG-Bench framework).
Research Experience
- Worked in Berkeley’s Artificial Intelligence (BAIR) Lab on projects at the intersection of AI security and model robustness.
Education
- Degree: Undergraduate; University: UC Berkeley; Advisors: Professor David Wagner and Chawin Sitawarin; Time: Not specified; Major: Computer Science.
Background
- Research Interests: AI security and model robustness; Professional Field: Artificial Intelligence Security; Brief Introduction: First-year PhD student at Princeton, currently collaborating with Gray Swan AI.
Miscellany
- Email: huang33176 [at] berkeley [dot] edu
