10 citations · 12 across the 12 of their papers we have counts for
14 papers
PruneForget: Joint Unlearning and Pruning of Vision Models
Yu-Shan Tai, Amber Yijia Zheng, Raymond A. Yeh
Machine unlearning and model pruning are increasingly coupled in the real world. Models must support unlearning requests, e.g., for safety concerns, while also meeting requirements…
Spectral Saliency for Machine Unlearning
Cedar Site Bai, Amber Yijia Zheng, Raymond A. Yeh +1
Machine unlearning (MU) aims to remove the influence of specific training data while preserving model utility. As the name suggests, MU can be viewed as the inverse of learning, us…
Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation
Amber Yijia Zheng, Lu Liu, Raymond A. Yeh +1
Text-to-video generation has advanced significantly over the past five years through scaling of model size, data, and compute. Unlike model architecture, training data is often und…
Designing to Forget: Deep Semi-parametric Models for Unlearning
Amber Yijia Zheng, Yu-Shan Tai, Raymond A. Yeh
Recent advances in machine unlearning have focused on developing algorithms to remove specific training samples from a trained model. In contrast, we observe that not all models ar…
WebAccessVL: Violation-Aware VLM for Web Accessibility
Amber Yijia Zheng, Jae Joong Lee, Bedrich Benes +1
We present a vision-language model (VLM) that automatically edits website HTML to address violations of the Web Content Accessibility Guidelines 2 (WCAG2) while preserving the orig…
Knowledge Distillation Detection for Open-weights Models
Qin Shi, Amber Yijia Zheng, Qifan Song +1
We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where on…
Model Immunization from a Condition Number Perspective
Amber Yijia Zheng, Cedar Site Bai, Brian Bullins +1
Model immunization aims to pre-train models that are difficult to fine-tune on harmful tasks while retaining their utility on other non-harmful tasks. Though prior work has shown e…
DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP
Amber Yijia Zheng, Yu Zhang, Jun Hu +2
High-quality photography in extreme low-light conditions is challenging but impactful for digital cameras. With advanced computing hardware, traditional camera image signal process…
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
Weichen Fan, Amber Yijia Zheng, Raymond A. Yeh +1
Classifier-Free Guidance (CFG) is a widely adopted technique in diffusion/flow models to improve image fidelity and controllability. In this work, we first analytically study the e…
Multi-concept Model Immunization through Differentiable Model Merging
Amber Yijia Zheng, Raymond A. Yeh
Model immunization is an emerging direction that aims to mitigate the potential risk of misuse associated with open-sourced models and advancing adaptation methods. The idea is to…
Learning to Obstruct Few-Shot Image Classification over Restricted Classes
Amber Yijia Zheng, Chiao-An Yang, Raymond A. Yeh
Advancements in open-source pre-trained backbones make it relatively easy to fine-tune a model for new tasks. However, this lowered entry barrier poses potential risks, e.g., bad a…
BloomGML: Graph Machine Learning through the Lens of Bilevel Optimization
Amber Yijia Zheng, Tong He, Yixuan Qiu +2
Bilevel optimization refers to scenarios whereby the optimal solution of a lower-level energy function serves as input features to an upper-level objective of interest. These optim…
IMMA: Immunizing text-to-image Models against Malicious Adaptation
Amber Yijia Zheng, Raymond A. Yeh
Advancements in open-sourced text-to-image models and fine-tuning methods have led to the increasing risk of malicious adaptation, i.e., fine-tuning to generate harmful/unauthorize…
Learning Manifold Dimensions with Conditional Variational Autoencoders
Yijia Zheng, Tong He, Yixuan Qiu +1
Although the variational autoencoder (VAE) and its conditional extension (CVAE) are capable of state-of-the-art results across multiple domains, their precise behavior is still not…