Tianshi Cao

Researcher, NVIDIA

PhD student, Computer Science, University of Toronto

Joined

October 2018

Names

Tianshi Cao (Preferred)

Emails

****@mail.utoronto.ca (Confirmed)

****@cs.toronto.edu (Confirmed)

****@nvidia.com (Confirmed)

Personal Links

Google Scholar

ORCID

Career & Education History

Researcher

NVIDIA (nvidia.com)

2025 – Present

PhD student

Computer Science, University of Toronto (utoronto.ca)

2021 – Present

Advisors, Relations & Conflicts

PhD Advisor

Sanja Fidler

2021 – 2026

Expertise

Video generative models

2024 – 2025

3D Vision

2023 – 2025

3D generative models

2023 – 2025

generative models

2018 – 2025

differential privacy

2020 – 2022

deep learning

2016 – 2020

Publications

ChronoEdit: Towards Temporal Reasoning for In-Context Image Editing and World Simulation
Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Tianshi Cao, Kai He, Yifan Lu, Ruiyuan Gao, Enze Xie, Shiyi Lan, Jose M. Alvarez, Jun Gao, Sanja Fidler, Zian Wang, Huan Ling
- ICLR 2026 Poster
- Readers: Everyone
LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis
Kevin Xie, Jonathan Lorraine, Tianshi Cao, Jun Gao, James Lucas, Antonio Torralba, Sanja Fidler, Xiaohui Zeng
- Crossref
- Readers: Everyone
Problems in the deployment of machine-learned models in health care
Joseph Paul Cohen, Tianshi Cao, Joseph D Viviano, Chin-Wei Huang, Michael Fralick, Marzyeh Ghassemi, Muhammad Mamdani, Russell Greiner, Yoshua Bengio
- 27 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Differentially Private Diffusion Models
Tim Dockhorn, Tianshi Cao, Arash Vahdat, Karsten Kreis
- Accepted by TMLR
- Readers: Everyone
How many trained neural networks are needed for influence estimation in modern deep learning?
Sasha Doubov, Tianshi Cao, David Acuna, Sanja Fidler
- Published: 06 Dec 2022, Last Modified: 05 May 2023
- ICBINB poster
- Readers: Everyone
Differentially Private Diffusion Models
Tim Dockhorn, Tianshi Cao, Arash Vahdat, Karsten Kreis
- Published: 01 Feb 2023, Last Modified: 12 Mar 2024
- Submitted to ICLR 2023
- Readers: Everyone
A Benchmark of Medical Out of Distribution Detection
Tianshi Cao, Chin-Wei Huang, David Yu-Tung Hui, Joseph Paul Cohen
- 08 Jun 2021 (modified: 26 May 2025)
- Submitted to NeurIPS 2021 Datasets and Benchmarks Track (Round 1)
- Readers: Everyone
Scalable Neural Data Server: A Data Recommender for Transfer Learning
Tianshi Cao, Sasha Doubov, David Acuna, Sanja Fidler
- Published: 09 Nov 2021, Last Modified: 26 May 2025
- NeurIPS 2021 Poster
- Readers: Everyone
Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
Tianshi Cao, Alex Bie, Arash Vahdat, Sanja Fidler, Karsten Kreis
- Published: 09 Nov 2021, Last Modified: 26 May 2025
- NeurIPS 2021 Poster
- Readers: Everyone
Differentially Private Generative Models Through Optimal Transport
Tianshi Cao, Alex Bie, Karsten Kreis, Sanja Fidler
- 28 Sept 2020 (modified: 05 May 2023)
- ICLR 2021 Conference Blind Submission
- Readers: Everyone

Co-Authors

View all 33 co-authors