Zihui Wu
7 papers · 2023–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
AAAI (2)
NIPS (2)
COLING (1)
CVPR (1)
ICLR (1)
Top co-authors
Keywords
large language model
(2)
image reconstruction
(2)
medical imaging
(1)
attention mechanism
(1)
posterior sampling
(1)
ai safety
(1)
graph attention
(1)
harmful content
(1)
safety alignment
(1)
markov chain monte carlo
(1)
discrete optimization
(1)
magnetic resonance imaging
(1)
spectral radius
(1)
diffusion model
(1)
graph attention network
(1)
jailbreak attack
(1)
bayesian inverse problem
(1)
model reliability
(1)
neural operator
(1)
node representation
(1)
Papers
GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization
AAAI 2026
HumorReject: Decoupling LLM Safety from Refusal Prefix via a Little Humor
AAAI 2026
InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences
ICLR 2025
A Unified Model for Compressed Sensing MRI Across Undersampling Patterns
CVPR 2025
The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models
COLING 2025
Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors
NIPS 2024
Demystifying Oversmoothing in Attention-Based Graph Neural Networks
NIPS 2023