Huan Ling


  • I am a Research Scientist at NVIDIA Toronto AI Lab. I am also a Phd candidate at University of Toronto, machine learning group and Vector Institute.
  • My advisor is Prof. Sanja Fidler.


    • Invited Talks:
  • - Aug 2024: From Video Diffusion Model to 4D Dynamic Content Creation , Peking University, Visual Computing and Learning Lab , Slides
  • - Oct 2023: See Through the Eyes of Generative Models , UBC
  • - July 2023: Computer vision generation and perception using Diffusion Models , ByteDance AD Core , Slides
  • - June 2023: Image, Video and 3D Content Creation with Diffusion Models , BAAI'2023 , Slides
  • - June 2023: Align your Latents: VideoLDM , Shanghai AI Lab , Slides
  • - July 2021: GANs for 2D Vision Perception , Walmart CV Conf , Slides
  • - June 2021: GANs for 2D Vision Perception , IIIS, Tsinghua University , Slides
    • Pro Bono:

  • As a relatively senior PhD student, who also worked as a research scientist. I always see the information asymmetry between junior students and senior students.
    Nowadays, as AI research goes so fast, I can especially feel the challenge for Undergrad/Junior students to start their career.
    Following Krishna, Wei-Chiu, Shangzhe and Jun , I decide to commit 1 hours per week to host free pro bono office hours to help reduce the information asymmetry mentioned above.

    Please send me an emial if you are interested.


Selected Publications

(Full list )

Generative Models

L4GM: Large 4D Gaussian Reconstruction Model
  • Jiawei Ren, Kevin Xie, Ashkan Mirzaei, Hanxue LIANG, Xiaohui Zeng,
    Karsten Kreis, Ziwei Liu, Antonio Torralba, Sanja Fidler, Seung Wook Kim, Huan Ling
  • Project Page


    • Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
  • Huan Ling*, Seung Wook Kim*, Antonio Torralba, Sanja Fidler, Karsten Kreis
    (*: equally contributed)
  • Project Page
  • Paper accepted by CVPR 2024 (Highlight)


    • Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
  • Andreas Blattmann*, Robin Rombach*, Huan Ling*, Tim Dockhorn*, Seung Wook Kim, Sanja Fidler, Karsten Kreis (*: equally contributed)
  • Project Page
  • Paper accepted by CVPR 2023
  • The follow up version developed by stability.ai is available at SVD. The team developed larger and carefully curated dataset and careful final fine-funing on high-quality data from end-to-end.
  • Media: Two minutes paper


    • EditGAN: High-Precision Semantic Image Editing
  • Huan Ling*, Karsten Kreis*, Daiqing Li, Seung Wook Kim, Antonio Torralba, Sanja Fidler (*: equally contributed)
  • Project Page
  • Code&Demo
  • Paper accepted by Neurips 2021
  • Media: Two minutes paper


    • Generative Representation Learning

    3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features
  • Chenfeng Xu, Huan Ling, Sanja Fidler, Or Litany
  • Project Page


    • DreamTeacher: Pretraining Image Backbones with Deep Generative Models
  • Daiqing Li*, Huan Ling*, Amlan Kar, David Acuna, Seung Wook Kim, Karsten Kreis, Antonio Torralba Sanja Fidler
    (*: equally contributed)
  • Project Page
  • Paper accepted by ICCV 2023


    • BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations
  • Daiqing Li, Huan Ling, Seung Wook Kim, Karsten Kreis, Adela Barriuso, Sanja Fidler, Antonio Torralba
  • Project Page
  • Code&Demo
  • Paper accepted by CVPR 2022


    • DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
  • Yuxuan Zhang*, Huan Ling*, Jun Gao, Kangxue Yin, Jean-Francois Lafleche, Adela Barriuso, Antonio Torralba, Sanja Fidler (*: equally contributed)
  • Project Page
  • Code&Data
  • Paper accepted by CVPR 2021


    • Variational Amodal Object Completion
  • Huan Ling*, David Acuna, Karsten Kreis, Seung Wook Kim, Sanja Fidler (*: equally contributed)
  • Project Page
  • Paper accepted by Neurips 2020


    • 3D Vision

    Image gans meet differentiable rendering for inverse graphics and interpretable 3d neural rendering
  • Yuxuan Zhang*, Wenzheng Chen*, Huan Ling, Yinan Zhang, Sanja Fidler (*: equally contributed)
  • Download Paper
  • Project Page
  • Paper accepted by ICLR 2021
  • Media: GANverse3D


    • Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
  • Wenzheng Chen, Jun Gao*, Huan Ling*, Edward J. Smith*, Jaakko Lehtinen, Alec Jacobson, Sanja Fidler (*: equally contributed)
  • Download Paper
  • Project Page
  • Paper accepted by Neural Information Processing Systems(NeurIPS), Vancouver, CA, 2019
  • Media: Two-minutes paper


    • Human in Loop

    ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
  • Bowen Chen*, Huan Ling*, Jun Gao, Xiaohui Zeng, Ziyue Xu, Sanja Fidler (*: equally contributed)
  • Download Paper
  • Project Page
  • European Conference on Computer Vision (ECCV), 2020


    • Fast Interactive Object Annotation with Curve-GCN
  • Huan Ling*, Jun Gao*, Amlan Kar, Wenzheng Chen, Sanja Fidler (*: equally contributed)
  • Download Paper
  • Code
  • Paper accepted by Conference on Computer Vision and Pattern Recognition(CVPR), Long Beach, US, 2019


    • Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
  • David Acuna*, Huan Ling*, Amlan Kar*, Sanja Fidler (*: equally contributed)
  • Demo Video
  • Download Paper
  • Paper accepted by Conference on Computer Vision and Pattern Recognition(CVPR), Salt Lake City, US, 2018


    • Teaching Machines to Describe Images with Natural Language Feedback
  • Huan Ling, Sanja Fidler
  • Project Page
  • Download Paper: arXiv preprint, May 2017
  • Paper accepted by Neural Information Processing Systems(NIPS), Long Beach, US, 2017
  • Fun note from year of 2023: Yes we took a bite of RLHF back to 2017 :)

      • Academic Service
      • Serve as the reviewer of ICCV'19, CVPR'19, Neurips'20, CVPR'21