Zhenyu Wen
4 papers · 2026–2026 · 2 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
domain generalization
(1)
test-time adaptation
(1)
text-to-image generation
(1)
backdoor attack
(1)
diffusion model
(1)
denoising process
(1)
adversarial example
(1)
edge deployment
(1)
attack transferability
(1)
latent diffusion model
(1)
memory constraint
(1)
expert prediction
(1)
clean-label attack
(1)
rf fingerprinting
(1)
physical information
(1)
wireless authentication
(1)
expert offloading
(1)
generative manifold
(1)
text trigger
(1)
dual-modality manipulation
(1)
Papers
Beyond Single-Point Perturbation: A Hierarchical, Manifold-Aware Approach to Diffusion Attacks
AAAI 2026
FIRM-MoE:Fine-GrainedExpert Decomposition for Resource-Adaptive MoE Inference
AAAI 2026
RFF-TTA: Physical Information-Aware Prototype for Temporally Varying RF Fingerprinting Online Test-Time-Adaptation
AAAI 2026
Towards Human-Imperceptible Backdoor Attacks on Text-to-Image Diffusion Models
CVPR 2026