| CARVIEW |
Amin Shabani
ML Researcher at RBC Borealis
I received my Ph.D. in Computer Science from Simon Fraser University (SFU) under the supervision of Prof. Yasutaka Furukawa, and my M.Sc. from Seoul National University (SNU) under Prof. Kyoung Mu Lee.
Research Interests
Generative Models
Exploring advanced generative models, including diffusion models, for diverse data synthesis.
Time Series Forecasting
Developing robust models for predicting future data points in time-dependent sequences.
Large Language Models
Researching capabilities of large language models for NLP tasks.
News
October 2025 1st Place Winner, Financial Agentic Retrieval Grand Challenge (FinAgentBench), AI for Finance Symposium ’25. (new)
September 2025 New arXiv preprint: "Embedding-based Context-aware Reranker". (new)
September 2025 Paper "FACTS: Table Summarization via Offline Template Generation wtih Agentic Workflows" accepted at NeurIPS 2025 Workshop on Generative AI in Finance. (new)
April 2024 Joined RBC Borealis as a Machine Learning Researcher.
March 2024 Paper "Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation" accepted at CVPR 2024.
January 2024 Gave a talk about my research on diffusion models for layout generation at Samsung AI Center in Toronto.
September 2023 Paper "PuzzleFusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving" accepted as Spotlight at NeurIPS 2023.
March 2023 Paper "HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising" accepted at CVPR 2023.
January 2023 Paper "Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting" accepted at ICLR 2023.
Photos
Work Experience
Machine Learning Researcher
Apr 2024 - PresentContributing to research and development of machine learning models for real-world applications in finance.
Research Scientist/Engineer Intern
Jun 2023 - Nov 2023Worked on a new method for automatically generating layout designs. Published at CVPR 2024.
View PublicationMachine Learning Research Intern
Jan 2022 - May 2022Worked on Iterative Multi-scale Refining Transformers for Time Series Forecasting. Published at ICLR 2023.
View PublicationResearch and Development Engineer
Feb 2017 - Aug 2017Worked on finding online methods for object detection, considering the trade-off between speed and accuracy.
Education
Simon Fraser University
2019 - 2025Ph.D. (Doctor of Philosophy)
Computer Science
Seoul National University
2017 - 2019M.Sc. (Master of Science)
Computer Engineering
Sharif University of Technology
2012 - 2017B.Sc. (Bachelor of Science)
Computer Science
Publications
FACTS: Table Summarization via Offline Template Generation wtih Agentic Workflows
NeurIPS Workshop, 2025Ye Yuan, Amin Shabani, Siqi Liu
Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation
CVPR 2024Amin Shabani, Zhaowen Wang, Difan Liu, Nanxuan Zhao, Jimei Yang, Yasutaka Furukawa
PuzzleFusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving
NeurIPS 2023 (Spotlight)Sepidehsadat Hosseini, Amin Shabani, Saghar Irandoust, and Yasutaka Furukawa
HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising
CVPR 2023Amin Shabani, Sepidehsadat Hosseini, and Yasutaka Furukawa
Vectorizing Building Blueprints
ACCV 2022Weilian Song, Mahsa Maleki Abyaneh, Amin Shabani, and Yasutaka Furukawa
Extreme Structure from Motion for Indoor Panoramas without Visual Overlaps
ICCV 2021Amin Shabani, Weilian Song, Makoto Odamaki, Hirochika Fujiki, and Yasutaka Furukawa
On decomposing complete tripartite graphs into 5-cycles
arXiv preprintM Abdolmaleki, SG Ilchi, ES Mahmoodian, MA Shabani
On Uniquely k-List Colorable Planar Graphs, Graphs on Surfaces, and Regular Graphs
Graphs and Combinatorics, 2018M Abdolmaleki, J. P. Hutchinson, S. Gh. Ilchi, E. S. Mahmoodian, N Matsumoto, M. A. Shabani
Get In Touch
Contact Information
Location
Vancouver, Canada