Year: 2026
Type: conference-paper
Abstract: Modern generative models still lack humanlevel creativity, particularly in multi-branch diversity.Prior approaches to address this problem often incur heavy computation or strong dependency on model architecture.Therefore, we introduce UAG(Universal Avoidance Generation), a model-agnostic and computationally efficient generation strategy that penalizes similarity among previously generated outputs.Thus, UAG can enhance multi-branch diversity across both diffusion and transformer models, with minimal additional computation.In experiments, our method achieves up to 1.9 times higher diversity, runs 4.4 times faster, and requires only 1/64 of the FLOPs compared to state-of-the-art methods.The full code is here.
Authors: Kyeongman Park, Minha Jhang, Kyomin Jung
Institution: Seoul National University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166810052