Zongqi Wang
6 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(3)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(11)
π§
Keyword Pioneer
π
Cross-Pollinator
(14)
Conferences
ACL (4)
AAAI (1)
EMNLP (1)
Top co-authors
Keywords
large language model
(3)
feature extraction
(1)
token selection
(1)
text generation
(1)
deepfake detection
(1)
ai safety
(1)
safety alignment
(1)
hierarchical taxonomy
(1)
bias mitigation
(1)
text watermarking
(1)
latent space
(1)
copyright protection
(1)
robustness evaluation
(1)
watermark removal
(1)
adaptive method
(1)
racial bia
(1)
fine-grained evaluation
(1)
token sampling
(1)
embedding watermarking
(1)
forgery detection
(1)
Papers
SCAN: Structured Capability Assessment and Navigation for LLMs
ACL 2026
Probing the Safety Robustness of LLMs in Latent Space
ACL 2026
Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations
AAAI 2025
MorphMark: Flexible Adaptive Watermarking for Large Language Models
ACL 2025
Robust and Minimally Invasive Watermarking for EaaS
ACL 2025
Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking
EMNLP 2025