Zhengyue Zhao
4 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Cross-Pollinator (4) π§ Keyword Pioneer π Conference Polyglot (3) πΊοΈ Taxonomy Completionist (12) π Renaissance Researcher (6)
π
Interdisciplinary Bridge
β
The Questioner
(2)
Conferences
AAAI (1)
CVPR (1)
ICLR (1)
IJCAI (1)
Top co-authors
Research topics
Keywords
preference alignment
(1)
safety alignment
(1)
boolean function
(1)
adversarial perturbation
(1)
stable diffusion
(1)
privacy protection
(1)
soft prompt
(1)
prompt tuning
(1)
risc-v processor
(1)
electronic design automation
(1)
circuit synthesis
(1)
cpu design
(1)
input-output example
(1)
image purification
(1)
copyright infringement
(1)
harmful response
(1)
protective perturbation
(1)
facial privacy
(1)
cpu design automation
(1)
binary speculative diagram
(1)
Papers
Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
AAAI 2026
Can Watermarks be Used to Detect LLM IP Infringement For Free?
ICLR 2025
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
CVPR 2024
Automated CPU Design by Learning from Input-Output Examples
IJCAI 2024