TreeReward aims to enhance diffusion models from various aspects including Content, Style, Color, Lighting, Detail, and Layout. The radar chart visually ...
Built upon this dataset, we introduce a tree-structure reward model to exploit the fine-grained feedback data efficiently and provide tailored optimization ...
7 days ago · Built upon this dataset, we introduce a tree-structure reward model to exploit the fine-grained feedback data efficiently and provide tailored ...
Unifl: Improve stable diffusion via unified feedback learning. J Zhang, J ... 2024. TreeReward: Improve Diffusion Model via Tree-Structured Feedback Learning.
2024. TreeReward: Improve Diffusion Model via Tree-Structured Feedback Learning. J Zhang, J Wu, H Kuang, H Zhang, Y Ren, W Chen, M Zhang, X Xiao, ... ACM ...
Jiacheng Zhang's 6 research works with 53 citations, including: TreeReward: Improve Diffusion Model via Tree-Structured Feedback Learning.
Haiming Zhang's 1 research works with 0 citations, including: TreeReward: Improve Diffusion Model via Tree-Structured Feedback Learning.
TreeReward: Improve Diffusion Model via Tree-Structured Feedback Learning. 2024-10-28 | Conference paper. DOI: 10.1145/3664647.3680610. Contributors: Jiacheng ...
May 28, 2024 · This paper tackles the challenge of improving discrete diffusion models by introducing a structured forward process that leverages the inherent information ...
Missing: TreeReward: Tree- Feedback
Our work represents a novel methodological advance in generative modeling to structure the embedding space of diffusion models using tree-based knowledge.