no code implementations • 3 Feb 2024 • Yiping Wang, Yifang Chen, Wendan Yan, Kevin Jamieson, Simon Shaolei Du
In recent years, data selection has emerged as a core issue for large-scale visual-language model pretraining, especially on noisy web-curated datasets.
1 code implementation • 1 Oct 2023 • Yuandong Tian, Yiping Wang, Zhenyu Zhang, Beidi Chen, Simon Du
We propose Joint MLP/Attention (JoMA) dynamics, a novel mathematical framework to understand the training procedure of multilayer Transformer architectures.
no code implementations • 5 Jun 2023 • Yiping Wang, Yifang Chen, Kevin Jamieson, Simon S. Du
In addition to our sample complexity results, we also characterize the potential of our $\nu^1$-based strategy in sample-cost-sensitive settings.
1 code implementation • 11 Oct 2022 • Huaxiu Yao, Yiping Wang, Linjun Zhang, James Zou, Chelsea Finn
In this paper, we propose a simple yet powerful algorithm, C-Mixup, to improve generalization on regression tasks.
no code implementations • 14 Oct 2021 • Ahmad Pesaranghader, Yiping Wang, Mohammad Havaei
Diversity in data is critical for the successful training of deep learning models.
no code implementations • ICML Workshop URL 2021 • Yiping Wang, Michael Brandon Haworth
We qualitatively and quantitatively demonstrate that, in terms of multi-agent ($\geq$ 8 agents) navigation and steering, $\textit{Students}$ trained by our approach outperform agents using heuristic search, as well as agents trained by domain randomization.
no code implementations • 8 Dec 2020 • Mohammad Havaei, Ximeng Mao, Yiping Wang, Qicheng Lao
Current practices in using cGANs for medical image generation, only use a single variable for image generation (i. e., content) and therefore, do not provide much flexibility nor control over the generated image.
1 code implementation • MIDL 2019 • Yiping Wang, David Farnell, Hossein Farahani, Mitchell Nursey, Basile Tessier-Cloutier, Steven J. M. Jones, David G. Huntsman, C. Blake Gilks, Ali Bashashati
The proposed algorithm achieved a mean accuracy of $87. 54\%$ and Cohen's kappa of $0. 8106$ in the slide-level classification of $305$ WSIs; performing better than a standard CNN and pathologists without gynecology-specific training.