no code implementations • 3 Feb 2024 • Yifei He, Shiji Zhou, Guojun Zhang, Hyokun Yun, Yi Xu, Belinda Zeng, Trishul Chilimbi, Han Zhao
To overcome this limitation, we propose Multi-Task Learning with Excess Risks (ExcessMTL), an excess risk-based task balancing method that updates the task weights by their distances to convergence instead.
no code implementations • 11 Dec 2023 • Savya Khosla, Zhen Zhu, Yifei He
This paper explores Memory-Augmented Neural Networks (MANNs), delving into how they blend human-like memory processes into AI.
1 code implementation • 20 Oct 2023 • Yifei He, Haoxiang Wang, Bo Li, Han Zhao
Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way.
no code implementations • 22 Oct 2022 • Runxiang Cheng, Gargi Balasubramaniam, Yifei He, Yao-Hung Hubert Tsai, Han Zhao
We formulate a theoretical framework for optimizing modality selection in multimodal learning and introduce a utility measure to quantify the benefit of selecting a modality.
no code implementations • 14 Jul 2022 • Yifei He, Artur Podobas, Måns I. Andersson, Stefano Markidis
Discrete Fourier Transform (DFT) libraries are one of the most critical software components for scientific computing.
no code implementations • 22 Jul 2020 • Linnea Grans-Samuelsson, Lawrence Liu, Yifei He, Jesper Lykke Jacobsen, Hubert Saleur
Here, we solve the problem for generic values of $Q$.
High Energy Physics - Theory Statistical Mechanics Mathematical Physics Mathematical Physics