no code implementations • 7 Mar 2024 • Nabil Ibtehaz, Ning Yan, Masood Mortazavi, Daisuke Kihara
At present two classes of attentions prevail in vision transformers, regional and sparse attention.
no code implementations • 23 Oct 2023 • Yihong Ma, Ning Yan, Jiayu Li, Masood Mortazavi, Nitesh V. Chawla
The surge in prompt-based learning within Natural Language Processing (NLP) suggests the potential of adapting a "pre-train, prompt" paradigm to graphs as an alternative.
no code implementations • 28 Jun 2023 • Chuanyue Shen, Letian Zhang, Zhangsihao Yang, Masood Mortazavi, Xiyun Song, Liang Peng, Heather Yu
Efficient photorealistic rendering of human 3D dynamics is the core of immersive meetings.