Amber Yijia Zheng

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

I'm currently a Research Scientist Intern at Meta GenAI, working with Xi Yin on post-training of video models. I've had pleasure to work with Chen Chen at Apple, David Wipf and Tong He at AWS AI Lab.

My research interests lie in generative models and general machine learning. Currently, I am interested in retrieval-augmented architecture design and model immunization. I also have great interest in post-training of image/video models. Please feel free to reach out via email!

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

arXiv

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

arXiv

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%)

Paper Project Page arXiv Code

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%)

Paper Project Page arXiv Code

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

Project Page arXiv Code

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

Project Page arXiv Code

Multi-concept Model Immunization through Differentiable Model Merging
Multi-concept Model Immunization through Differentiable Model Merging

Amber Yijia Zheng, Raymond A. Yeh

AAAI 2025

Paper Project Page arXiv Code

Multi-concept Model Immunization through Differentiable Model Merging
Multi-concept Model Immunization through Differentiable Model Merging

Amber Yijia Zheng, Raymond A. Yeh

AAAI 2025

Paper Project Page arXiv Code

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

Paper Project Page arXiv Code

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

Paper Project Page arXiv Code

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)

Paper Project Page arXiv Code

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)

Paper Project Page arXiv Code

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

Paper arXiv Code

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

Paper arXiv Code

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

Paper arXiv Code

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

Paper arXiv Code

All publications
Services

Conference reviewer: NeurIPS (2023, 2024, 2025), ICLR (2024, 2025), CVPR (2024, 2025), ICCV (2025)

Awards
  • ICLR Notable Reviewer 2025
  • Best paper Runner-up in AI4CC at CVPR 2024
  • NeurIPS Scholar Award 2022
  • Shanghai Outstanding Graduate 2022
  • First-class People's Scholarship 2020, 2021, 2022