Reproduce “Zellige: Moldable Sequence Placement for Mixed Image-Video DiT Training” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Guangyu Xiang, Xueze Kang, Minwei Zhao, Yuxin Wang, Shaohuai Shi, Lin Zhang, Xiaowen Chu
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.