31 citations · 40 across the 9 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024★ 1 cited
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…
cs.LG2024
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…