Xiaoyue Wang

SON: Enhancing Prompt Understanding of Diffusion Models with Large Language Models Guided Layouts

This work introduces SON-1K, a comprehensive benchmark for text-to-image generation, and proposes a new approach, the enhanced LMDpp, enhancing the performance of the novel two-stage Large Language Model (LLM)-grounded diffusion model pipeline (LMD).

Tri-driven graph reinforcement learning for dynamic root cause tracing in UF-RO water treatment processes