This study investigates how transformers learn through multi-head attention in regression tasks.
Xingwu Chen, Lei Zhao, Difan Zou
― 6 min read
Difan Zou
Investigating the impact of Sparse Rate Reduction on Transformer model performance.
Yunzhe Hu, Difan Zou, Dong Xu
― 6 min read
Discover how parallelized generation transforms image and video production.
Yuqing Wang, Shuhuai Ren, Zhijie Lin
― 5 min read