Angel Xuan Chang

I am an Assistant Professor at Simon Fraser University. Prior to this, I was a visiting research scientist at Facebook AI Research and a research scientist at Eloquent Labs working on dialogue. I received my Ph.D. in Computer Science from Stanford, where I was part of the Natural Language Processing Group and advised by Chris Manning. My research focuses on connecting language to 3D representations of shapes and scenes and grounding of language for embodied agents in indoor environments. I have worked on methods for synthesizing 3D scenes and shapes from natural language, and various datasets for 3D scene understanding. In general, I am interested in the semantics of shapes and scenes, the representation and acquisition of common sense knowledge, and reasoning using probabilistic models. Some of my other interests include drawing and dance.

      angelx-{at}-sfu-[dot]-ca
    

Assistant Professor
School of Computing Science
Simon Fraser University
GrUVi Lab | SFU NatLang | SFU AI/ML
Canada CIFAR AI Chair (Amii)
TUM-IAS Hans Fischer Fellow
Google Scholar

News

January 7, 2023 - Keynote at WACV 2023 workshop on Photorealistic Image and Environment Synthesis for Computer Vision (PIES-CV).
December 15, 2022 - Invited talk at CoRL 2022 workshop on Learning, Perception, and Abstraction for Long-Horizon Planning.
December 2022 - Habitat Rearrangement Competition (Dec 8th) at NeurIPS 2022.
October 2022 - Workshops at ECCV 2022.
- Oct 23rd - Workshop on Language for 3D Scenes
- Oct 23rd - Workshop on Learning to Generate 3D Shapes and Scenes
September 2022 - One paper accepted at NeurIPS 2022. Congratulations to Yongsen, Yiming, and Shawn for their work on MultiScan.
September 2022 - One paper accepted at 3DV 2022. Congratulations to Sanjay, Xiaohao, and Shawn for their work on understanding articulated 3D human-object interactions.
July 2022 - Two papers accepted at ECCV 2022. Congratulations to
- Dave and Qirui for their work on D3Net, a speaker-listener model for 3D visual grounding and captioning
- Shawn and Yongsen for their work on OPDet for openable part detection from single-view images
June 2022 - Workshops and Tutorials at CVPR 2022.
- June 19th - ScanNet Indoor Scene Understanding Challenge
- June 19th - Multi-Object Navigation Challenge at the Embodied-AI workshop
- June 20th - Tutorial: Building and Working in Environments for Embodied AI
June 2022 - 3DVQA work by Yasaman and Leon will be presented at CRV 2022.
April 2022 - Congratulations to Ali Gholami and Yue Ruan for defending their MSc thesis!
March 2022 - I'm excited to be part of BIOSCAN, a large, world-wide collaboration to identify and categorize the species of the world, and understand how they interact. I'm looking for a postdoc to use the latest advances in machine learning to develop algorithms to contribute to this project.
February 2022 - We are hosting the Multi-Object Navigation challenge, as part of the embodied AI workshop at CVPR 2022.
January 2022 - I'm happy to be hosting Dave Zhenyu Chen and Tommaso Campari as visiting students this term at SFU.
October 2021 - Habitat 2.0 to be presented at NeurIPS 2021 as a spotlight, and HM3D accepted to NeurIPS 2021 datasets and benchmarks.
September 2021 - Short paper on using language-aligned waypoints for supervising VLN-CE accepted to EMNLP 2021. Congratulations to Sonia, Shivansh, Saim, and Unnat!
August, 2021 - Congratulations to Leon Kochiev for defending his MSc thesis!
July, 2021 - Paper studying communication mechanisms between embodied AI agents for navigation accepted at ICCV 2021. Great job by Shivansh, Saim and Unnat!
July 10-14 2021 - SGP (Symposium for Geometry Processing) happening virtually!
June 2021 - Roominoes accepted to SGP 2021. Congratulations to Kai!
May 2021 - Challenges and Workshops at CVPR 2021.
- June 19th - 3D Vision and Robotics
- June 20th - ScanNet Indoor Scene Understanding Challenge
- June 20th - Multi-Object Navigation Challenge at the Embodied-AI workshop
- June 25th - Learning to Generate 3D Shapes and Scenes
- June 25th - Language for 3D Scenes
March 2021 - Three papers accepted at CVPR 2021. Great job by Madhawa, Qirui, Jiaqi, Lewis, Dave, and Ali!
January 2021 - I'm co-chairing SGP (Symposium for Geometry Processing) with Alec Jacobson.
November 25, 2020 - Invited talk at Emerging Technologies: BC's AI Showcase
November, 2020 - Whitepaper on Rearrangement: A Challenge for Embodied AI
October, 2020 - Papers accepted at UIST 2020, 3DV 2020, and NeurIPS 2020
July 16, 2020 - Lecture on natural language processing at Invent the Future: AI Scholars Program at Simon Fraser University
July 9, 2020 - Invited talk at the Workshop on Advances in Language and Vision Research (ALVR) at ACL 2020
July 8, 2020 - ScanNet received the Symposium on Geometry Processing (SGP) dataset award.
July, 2020 - Paper on localizing objects based on natural language descriptions in 3D scans (ScanRefer) is accepted at ECCV 2020.
June, 2020 - I'm co-organizing three workshops at CVPR 2020
- June 14th - Learning 3D Generative Models (CVPR daily)
- June 14-15th - Embodied-AI Workshop
- June 19th - ScanNet Indoor Scene Understanding Challenge (CVPR daily)
February, 2020 - Paper on simulation platform with articulated parts (SAPIEN) is accepted at CVPR 2020.
January, 2020 - I'm teaching CMPT 825 Natural language Processing this spring
August, 2019 - I started as assistant professor at Simon Fraser University
July, 25, 2019 - Lecture on deep learning for images at the DLRL Summer School at University of Alberta
July 18, 2019 - Lecture on natural language processing at Invent the Future: AI Scholors Program at Simon Fraser University
June 17, 2019 - Invited talk at the 360 Indoor Scene Understanding and Modeling (SUMO) workshop at CVPR
May, 2019 - I'm visiting Facebook AI Research this summer
March, 2019 - PartNet prerelease v0 is now available!
March, 2019 - Two upcoming workshops at CVPR 2019: 3D Scene Generation workshop and Scannet Indoor Scene Understanding workshop
March, 2019 - Three papers accepted at CVPR 2019
Dec 3, 2018 - I'm honored to be named to the first cohort of CIFAR AI Chairs.
Sept 9, 2018 - Visual Learning and Embodied Agents in Simulation Environments at ECCV 2018.
Sept, 2018 - Visiting Matthias Niessner at TUM.
July 11, 2018 - ShapeNet received the Symposium on Geometry Processing (SGP) dataset award.
June 29, 2018 - Invited talk at RSS 2018 workshop on New Benchmarks, Metrics, and Competitions for Robotic Learning.
June 11, 2018 - ScanNet v2 release and ScanNet Benchmark challenge announced.
June 3, 2018 - I joined Eloquent Labs.
May 2018 - Co-organizing ECCV 2018 workshop on Visual Learning and Embodied Agents in Simulation Environments.
March 2018 - I was awarded the TUM-IAS Hans Fischer Fellowship.