Curriculum Vitae

Download CV here

Education

BEng in Artificial Intelligence: Systems and Technologies (AIST), The Chinese University of Hong Kong, 2020-2024 (expected)
- Major GPA: 3.807/4.000
Diocesan Girls’ School, 2015-2020
- Mathematics Extended Module 2, Physics, ICT, Literature in English
The Deep Learning Specialization, Deeplearning.ai, Coursera, 2018
- https://coursera.org/share/79cb80a49acd6d0fe866c9d61702362c
Hong Kong Academy for Gifted Education, 2016-2020

Work experience

Mila Research Intern (upcoming)
- May - Aug 2023 (107 days)
- Mila—Quebec Artificial Intelligence Institute
- Project: Tbc
- Supervisor: Yann Dauphin and Aaron Courville
MPI-IS Research Intern
- Jan - Apr 2023 (3 months)
- Robust Machine Learning group, Max Planck Institute for Intelligent Systems, Tübingen
- Project: Sparse adversarial attacks and training
- Supervisor: Wieland Brendel
Stanford AI Lab (SAIL) Research Intern (remote)
- Jan - Jun 2022 (6 months)
- SAIL, Stanford Univeristy
- Project: Scene understanding via image intrinsics
- Supervisor: Jiajun Wu
NVIDIA Research Intern
- Sep 2020 - Oct 2021 (1 year)
- NVIDIA AI Technology Center, Hong Kong
- Projects: Multi-modal video generation, GAN mode-collapse problem, SSL
- Supervisors/Collaborators: Charles Cheung; briefly with Ming-Yu Liu, Arun Mallya, Ting-Chun Wang
Theoretical Machine Learning Lab Research Assistant
- Jan 2022 - Present (1 year, 3 months and counting)
- The Chinese University of Hong Kong
- Projects: Adversarial training and robustness; understanding generalisation; MixUp
- Supervisor: Farzan Farnia
- Publications:
  - Ching Lam Choi, Farzan Farnia, “Universal Adversarial Directions”, arXiv preprint arXiv:2210.15997, 2022.
  - Ching Lam Choi, Farzan Farnia, “Generalization of Interpretable Deep Learning Requires More Data”, 2023.
Multimedia Laboratory (MMLab) Research Student
- Jun 2019 - Jul 2022 (3 years)
- MMLab, The Chinese University of Hong Kong
- Supervisor: Hongsheng Li
- Publications:
  - Rui Liu, Yixiao Ge, Ching Lam Choi, Xiaogang Wang and Hongsheng Li, “DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network”, in CVPR, 2021.
  - Yixiao Ge, Xiao Zhang, Ching Lam Choi, Peipei Zhao, Feng Zhu, Rui Zhao, Hongsheng Li, “Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification”, arXiv preprint arXiv:2104.13298, 2021.
UG Summer Research Intern
- Jun - Aug 2021 (2 months)
- Engineering Faculty, The Chinese University of Hong Kong
- Project: Optimization Methods for Machine Learning
- Supervisor: Anthony Man-Cho So

Skills

Computer Vision
Machine Learning
Deep Learning
Research

Publications

DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network

Rui Liu, Yixiao Ge, Ching Lam Choi, Xiaogang Wang and Hongsheng Li. DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network. In IEEE Conference on Computer Vision and Pattern Recognition, 2021.

Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification

Yixiao Ge, Xiao Zhang, Ching Lam Choi, Peipei Zhao, Feng Zhu, Rui Zhao, Hongsheng Li. Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification. arXiv preprint arXiv:2104.13298, 2021.

Universal Adversarial Directions

Ching Lam Choi, Farzan Farnia. Universal Adversarial Directions. arXiv preprint arXiv:2210.15997, 2022.

On the Generalization of Gradient-based Neural Network Interpretations

Ching Lam Choi, Farzan Farnia. On the Generalization of Gradient-based Neural Network Interpretations. 2023.

Service and leadership

AI Code-In Founder
Julia Community Student Club Leader 2020
Hong Kong Joint School Electronics and Computer Society (HKJSECS): 40th President

Ching Lam Choi

Curriculum Vitae

Education

Work experience

Skills

Publications

DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network

Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification

Universal Adversarial Directions

On the Generalization of Gradient-based Neural Network Interpretations

Talks

[PyCon HK 2020] Fighting COVID-19 with Machine Learning

[HKOSCon 2020] Julia – Looks like Python, feels like Lisp, runs like C/Fortran

[EuroPython 2020] Corona-Net: Fighting COVID-19 With Computer Vision

[JuliaCon 2020] Julia Track Google Code In and Beyond

[PyCon Taiwan 2020] Corona-Net: Fighting COVID-19 with Machine Learning

Projects

Elesafer: Security With Machine Learning

Corona-Net: Fighting COVID-19 With Computer Vision

MAESTRO.ai TaiChi Tutor

Service and leadership