Zongyu Wu
8 papers · 2024–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Silver
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(19)
โ
The Questioner
Top co-authors
Research topics
Keywords
large language model
(4)
contrastive learning
(1)
generative model
(1)
catastrophic forgetting
(1)
domain adaptation
(1)
multimodal learning
(1)
model unlearning
(1)
text-to-image generation
(1)
instruction following
(1)
machine unlearning
(1)
ai safety
(1)
constraint satisfaction
(1)
embedding similarity
(1)
backdoor attack
(1)
reinforcement learning
(1)
diffusion model
(1)
adversarial defense
(1)
image corruption
(1)
node classification
(1)
model quantization
(1)
Papers
Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
EACL 2026
Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models
EACL 2026
Catastrophic Failure of LLM Unlearning via Quantization
ICLR 2025
Divide-Verify-Refine: Can LLMs Self-align with Complex Instructions?
ACL 2025
Robustness Inspired Graph Backdoor Defense
ICLR 2025
Test-Time Multimodal Backdoor Detection by Contrastive Prompting
ICML 2025
Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
NeurIPS 2024
Universal Prompt Optimizer for Safe Text-to-Image Generation
NAACL 2024