Yujun Shen (Damon)



Google scholar  /  Github  /  LinkedIn  /  Email

Biography

Yujun Shen is currently a senior research scientist at Ant Research, leading the Interatcion Intelligence Lab. His research focuses on computer vision and deep learning, particularly on generative models and 3D vision.


News

  • [09/2023] 8 papers, including 2 Datasets & Benchmarks Track, accepted to NeurIPS 2023 (New Orleans, U.S.).
  • [08/2023] 1 paper, including 1 journal, accepted to SIGGRAPH Asia 2023 (Sydney, Australia).
  • [08/2023] 1 paper (IDInvert) included in TPAMI 2023.
  • [07/2023] 5 papers accepted to ICCV 2023 (Paris, France).
  • [04/2023] 1 paper accepted to ICML 2023 (Hawaii, U.S.).
  • [03/2023] 8 papers, including 1 highlight, accepted to CVPR 2023 (Vancouver, Canada).
  • [01/2023] 1 paper accepted to ICLR 2023 (Kigali, Rwanda).
  • [10/2022] 1 paper (GH-Feat) included in TPAMI 2022.
  • [09/2022] 4 papers, including 2 spotlight, accepted to NeurIPS 2022 (New Orleans, U.S.).
  • [07/2022] 2 papers, including 1 oral, accepted to ECCV 2022 (Tel Aviv, Israel).
  • [05/2022] 1 paper accepted to ICML 2022 (Baltimore, U.S.).
  • [03/2022] 4 papers, including 1 oral, accepted to CVPR 2022 (New Orleans, U.S.).
  • [09/2021] 2 papers accepted to NeurIPS 2021 (Virtual).
  • [03/2021] 5 papers, including 2 oral and 2 workshop, accepted to CVPR 2021 (Virtual).
  • [12/2020] 1 paper (HiGAN) included in IJCV 2021.
  • [10/2020] 1 paper (InterFaceGAN) included in TPAMI 2020.
  • [07/2020] 1 paper accepted to ECCV 2020 (Virtual).
  • [02/2020] 2 papers accepted to CVPR 2020 (Virtual).

Softwares

  • [09/2023] We release Aurora, the first open-sourced GAN-based text-to-image generation model.
  • [08/2023] We release CoDeF, which introduces a novel video representation.
  • [07/2023] We release Carver, a highly modularized codebase for 3D-aware image synthesis.
  • [07/2023] We release PoF3D, DiscoScene, GeoD, DepthGAN, VolumeGAN, to facilitate 3D-aware image synthesis.
  • [06/2023] We release VideoComposer, Composer, following a compositional paradigm for content creation.
  • [06/2023] We release StyleSV, a strong baseline for video generation.
  • [06/2023] We release GLeaD, DynamicD, EqGAN, InsGen, to facilitate GAN training.
  • [10/2022] We public a collection of studies on 3D generative models.
  • [07/2022] We release PadInv, GH-Feat, IDInvert, to facilitate GAN inversion and its applications.
  • [06/2022] We release ReSeFa, LowRankGAN, SeFa, HiGAN, InterFaceGAN, to facilitate interpretation of generative models.
  • [02/2022] We release Hammer, a sufficiently upgraded version of GenForce, to facilitate the training of deep models.
  • [09/2020] We release GenForce, an efficient PyTorch library for deep generative modeling.

Recent Studies [Publication List]


Experiences

Ant Group
Apr. 2022 - Present
Senior Research Scientist
ByteDance
Mar. 2021 - Apr. 2022
Senior Researcher
Google
Nov. 2019 - May 2020
Software Engineer Intern
Facebook Reality Lab (FRL)
May 2019 - Sep. 2019
Research Intern
Google
Jul. 2018 - Dec. 2018
Software Engineer Intern
The Chinese University of Hong Kong
Aug. 2016 - May. 2021
Ph.D. Degree in Information Engineering
Tsinghua University
Aug. 2012 - Jul. 2016
Bachelor Degree in Electronic Engineering
Second Bachelor Degree in Management

Professional Activities

  • Conference reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, SIGGRAPH, SIGGRAPH Asia, AAAI
  • Journal reviewer: TPAMI, IJCV, ToG, TIP, TNNLS, TMM, Computers & Graphics, TVCJ