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
Yuandong Tian
Research Scientist
I am a Research Scientist at Meta Artificial Intelligence Research since Jan 2015. Before joining FAIR, I was a researcher/SWE in Google X, Self-driving Car team from Sep. 2013 to Jan. 2015. I received PhD in Robotics from Carnegie Mellon University in 2013 and B.S and M.S of Computer Science from Shanghai Jiao Tong University in 2005 and 2008. I am a recipient of ICCV 2013 Marr Prize Honorable Mentions for a hierarchical framework that gives globally optimal guarantees for non-convex non-rigid image deformation, and 2011 Microsoft Research PhD Fellowship.
Interests
Computer vision, machine Learning
Latest Publications
ICLR - 2022
FP-NAS: Fast Probabilistic Neural Architecture Search
Zhicheng Yan, Xiaoliang Dai, Peizhao Zhang, Yuandong Tian, Bichen Wu, Matt Feiszli
Learning Bounded Context-Free-Grammar via LSTM and the Transformer: Difference and Explanations
Hui Shi, Sicun Gao, Yuandong Tian, Xinyun Chen, Jishen Zhao
Understanding Dimensional Collapse in Contrastive Self-supervised Learning
Li Jing, Pascal Vincent, Yann LeCun, Yuandong Tian
Understanding Curriculum Learning in Policy Optimization for Solving Combinatorial Optimization Problems
Runlong Zhou, Yuandong Tian, Yi Wu, Simon S. Du
CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research
Chris Cummins, Bram Wasti, Jiadong Guo, Brandon Cui, Jason Ansel, Sahir Gomez, Somya Jain, Jia Liu, Olivier Teytaud, Benoit Steiner, Yuandong Tian, Hugh Leather
