1 citations · 2 across the 10 of their papers we have counts for
5 papers · 1 filter
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model
ZiDong Wang, Zeyu Lu, Di Huang +4
\textit{Nature is infinitely resolution-free}. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing imag…
Diffusion Models Need Visual Priors for Image Generation
Xiaoyu Yue, Zidong Wang, Zeyu Lu +5
Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from…
ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems
Xiangyuan Xue, Zeyu Lu, Di Huang +3
Much previous AI research has focused on developing monolithic models to maximize their intelligence, with the primary goal of enhancing performance on specific tasks. In contrast,…
PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines
ZiDong Wang, Zeyu Lu, Di Huang +4
In this paper, we introduce PredBench, a benchmark tailored for the holistic evaluation of spatio-temporal prediction networks. Despite significant progress in this field, there re…
FiT: Flexible Vision Transformer for Diffusion Model
Zeyu Lu, Zidong Wang, Di Huang +4
Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolut…