Authors

Chen Dai

Publications 2

Preprint Open access

DOGS: Design-Space Sampling for Prompt-Driven Logo Generation

Ganyu Zou, Chen Dai, Nathan Self et al. · 2026

Prompt optimization for text-to-image (T2I) generation has been pursued almost entirely as text rewriting, in which a short user brief is expanded into a longer, model-preferred token sequence. We argue that such a language-space formulation is ill-suited to structured visual design tasks such as logo creation, where a …

Preprint Open access

Compositional Concept Erasure in Text-to-Image Diffusion Models via Hierarchically Grounded Semantic Surgery

Chen Dai, Ganyu Zou, Nathan Self et al. · 2026

Removing copyrighted, unsafe, or user-specified concepts from a deployed text-to-image diffusion model is now a practical requirement. Weight-editing methods can suppress fixed targets, but they require per-target retraining and modify the model checkpoint. Training-free methods, on the other hand, are deployment-frien …

Co-authors