Ziqiang Li
10 papers · 2022–2026 · 5 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(17)
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Keywords
diffusion model
(3)
generative model
(2)
image generation
(2)
text-to-image generation
(2)
backdoor attack
(2)
trigger pattern
(2)
scene graph
(1)
visual representation learning
(1)
autoregressive model
(1)
disentangled representation
(1)
deep neural network
(1)
adversarial perturbation
(1)
variational autoencoder
(1)
virtual try-on
(1)
weak-to-strong generalization
(1)
concept erasure
(1)
poisoned sample
(1)
neural network
(1)
identity protection
(1)
content fidelity
(1)
Papers
Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
CVPR 2026
No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation
CVPR 2026
Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation
CVPR 2026
Closed-Loop Unsupervised Representation Disentanglement with \β-VAE Distillation and Diffusion Probabilistic Feedback
ECCV 2024
Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
ICLR 2024
Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm
ECCV 2024
Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
NeurIPS 2024
Domain Re-Modulation for Few-Shot Generative Domain Adaptation
NeurIPS 2023
Data-Efficient Backdoor Attacks
IJCAI 2022
FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs
ECCV 2022