Dilin Wang
Dilin Wang is a research scientist at Meta. Prior to joining Meta, Dilin earned his PhD from UT Austin, advised by Prof. Qiang Liu.
Dilin’s recent research focuses on developing algorithms that enable machines to better understand complex scenes as well as to generate content. In the meantime, he also places a strong emphasis on improving the efficiency of these algorithms for on-device settings.
Email: wdilin [at] meta.com
Google Scholar
|
|
MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction
Shitao Tang, Jiacheng Chen, Dilin Wang, Chengzhou Tang, Fuyang Zhang, Yuchen Fan, Vikas Chandra, Yasutaka Furukawa, Rakesh Ranjan
arxiv 2024
Project page
|
SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity
Peihao Wang, Zhiwen Fan, Dejia Xu, Dilin Wang, Sreyas Mohan, Forrest Iandola, Rakesh Ranjan, Yilei Li, Qiang Liu, Zhangyang Wang, Vikas Chandra
arxiv 2023
|
Taming Mode Collapse in Score Distillation for Text-to-3D Generation
Peihao Wang, Zhiwen Fan, Dejia Xu, Dilin Wang, Sreyas Mohan, Forrest Iandola, Rakesh Ranjan, Yilei Li, Qiang Liu, Zhangyang Wang, Vikas Chandra
arxiv 2023
|
Fast Point Cloud Generation with Straight Flows
Lemeng Wu, Dilin Wang, Chengyue Gong, Xingchao Liu, Yunyang Xiong, Rakesh Ranjan, Raghuraman Krishnamoorthi, Vikas Chandra, Qiang Liu
CVPR, 2023
arxiv /
code
|
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, Vikas Chandra
ICLR, 2022
paper /
code
|
AlphaNet: Improved Training of Supernets with Alpha-Divergence
Dilin Wang, Chengyue Gong, Meng Li, Qiang Liu, Vikas Chandra
ICML, 2021   (Long Talk 166/5513=3%)
arxiv /
code
|
Variational inference with tail-adaptive f-divergence
Dilin Wang, Hao Liu, Qiang Liu
NeurIPS, 2018   (Oral Presentation 30/4856=0.6%)
arXiv
|
Stein variational gradient descent: A general purpose bayesian inference algorithm
Qiang Liu, Dilin Wang
NIPS, 2016
paper /
code
|
|