NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict-aware Supernet Training
Chengyue Gong, Dilin Wang, Meng Li, Xinlei Chen, Zhicheng Yan, Yuandong Tian, Qiang Liu, Vikas Chandra
People
Dilin Wang
Research Scientist
I am a Research Scientist at Meta. My research interests are primarily in machine learning, with a focus on energy-efficient deep learning and AR/VR. I did my Ph.D. in CS at UT Austin, where I was advised by Qiang Liu.
Latest Publications
ICLR - 2022
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Dilin Wang, Chengyue Gong, Meng Li, Qiang Liu, Vikas Chandra
KeepAugment: A Simple Information-Preserving Data Augmentation Approach
Chengyue Gong, Dilin Wang, Meng Li, Vikas Chandra, Qiang Liu
AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
Dilin Wang, Meng Li, Chengyue Gong, Vikas Chandra