Amber Yijia Zheng

I am a Ph.D. student in Computer Science at Purdue University, advised by Prof. Raymond A. Yeh. I received my B.Sc. in Data Science from Shanghai University of Finance and Economics, where I worked with Prof. Yixuan Qiu.

I am currently a Research Scientist Intern at Meta GenAI, working with Xi Yin and Lu Liu as a core contributor to a large-scale video generation project. Previously, I worked with Chen Chen at Apple Camera, and with David Wipf and Tong He at AWS AI Lab.

My research interests include generative models, post-training for video and image generation, retrieval-augmented architectures, and model safety/immunization. I am passionate about building scalable, controllable generative systems that are both high-fidelity and safe. Please feel free to reach out via email!

Education
Aug. 2022 - present
Ph.D. Student in Computer Science
Purdue University
Sept. 2018 - Jul. 2022
B.sc. in Data Science
Shanghai University of Finance and Economics
Experience
May 2025 - Present
Research Scientist Intern
Meta GenAI
Apr. 2024 - Sept. 2024
Research Intern
Apple Camera
Feb. 2022 - Apr. 2024
Applied Scientist Intern
Amazon Web Services
May 2025
Our paper Model Immunization from a Condition Number Perspective is accepted as Oral in ICML 2025!
Dec 2024
Our paper Multi-concept Model Immunization through Differentiable Model Merging is accepted by AAAI 2025!
Dec 2024
I will join Meta Logo Meta GenAI as a Research Scientist Intern in 2025 summer.
Jul 2024
IMMA and LTO are accepted by ECCV 2024!
Jul 2024
Invited keynote speaker of T2MM @ICME 2024.
Jun 2024
IMMA is selected as an oral presentation and awarded 🥈 Best Paper Runner-up 🥈 at AI4CC @CVPR 2024!
Feb 2024
I will join  Apple as a Research Intern in 2024 summer.
Jan 2024
Our paper Graph Machine Learning through the Lens of Bilevel Optimization is accepted by AISTATS 2024!
Mar 2023
Invited speaker for Rising Star Lecture Series of ASTAR Center for Frontier AI Research (CFAR)
Oct 2022
I get NeurIPS 2022 Scholar Award.
Sep 2022
Our paper Learning Manifold Dimensions with Conditional Variational Autoencoders is accepted by NeurIPS 2022!
Aug 2022
I'm on boarding at Purdue as a PhD student. Boiler up!!
Jun 2022
I'm awarded Shanghai Outstanding Graduate and Honours Degree at Shanghai University of Finance and Economics.
Jul 2024
Invited keynote speaker
T2MM @ICME
Jun 2024
Oral presentation
AI for Content Creation Workshop @CVPR
Mar 2023
CFAR Rising Star speaker
Centre for Frontier AI Research, Singapore
Publications
DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP

DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP

Amber Yijia Zheng, Yu Zhang, Jun Hu, Raymond A. Yeh, Chen Chen
arXiv, 2025
Model Immunization from a Condition Number Perspective

Model Immunization from a Condition Number Perspective

Amber Yijia Zheng*, Site Bai*, Brian Bullins, Raymond A. Yeh (* equal contribution)
ICML 2025 Oral presentation (Top 1%)
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models

CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models

Weichen Fan, Amber Yijia Zheng, Raymond A. Yeh, Ziwei Liu
arXiv, 2025
Multi-concept Model Immunization through Differentiable Model Merging

Multi-concept Model Immunization through Differentiable Model Merging

Amber Yijia Zheng, Raymond A. Yeh
AAAI 2025
Learning to obstruct few-shot image classification over restricted classes

Learning to obstruct few-shot image classification over restricted classes

Amber Yijia Zheng*, Chiao-An Yang*, Raymond A. Yeh (* equal contribution)
ECCV 2024
IMMA: Immunizing text-to-image Models against Malicious Adaptation

IMMA: Immunizing text-to-image Models against Malicious Adaptation

Amber Yijia Zheng, Raymond A. Yeh
ECCV 2024
AI4CC Workshop in CVPR, 2024 (Best paper Runner-up)
Graph Machine Learning through the Lens of Bilevel Optimization

Graph Machine Learning through the Lens of Bilevel Optimization

Amber Yijia Zheng, Tong He, Yixuan Qiu, Minjie Wang, David Wipf
AISTATS 2024
Learning Manifold Dimensions with Conditional Variational Autoencoders

Learning Manifold Dimensions with Conditional Variational Autoencoders

Amber Yijia Zheng, Tong He, Yixuan Qiu, David Wipf
NeurIPS 2022
Conference reviewer
NeurIPS (2023, 2024, 2025), ICLR (2024, 2025), CVPR (2024, 2025), ICCV (2025)
Awards & Recognition
2025
ICLR Notable Reviewer
2024
Best paper Runner-up in AI4CC at CVPR
2022
NeurIPS Scholar Award
2022
Shanghai Outstanding Graduate
2020, 2021, 2022
First-class People's Scholarship