18 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…
Zero-shot 2D Grounding with Novel Affordance Types
Haomeng Zhang, Raymond A. Yeh
2D affordance grounding aims to locate the region of an object that a human can interact with. Existing research focuses on recognizing affordance types seen during training and do…
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…
DREAM-Chunk: Reactive Action Chunking with Latent World Model
Wenxi Chen, Kaidi Zhang, Chi Lin +6
Action chunking has become a common interface for vision-language-action (VLA) models, enabling low-frequency policy inference to drive high-frequency robot execution. However, onc…
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…
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
Chiao-An Yang, Ryo Hachiuma, Sifei Liu +4
Despite advances in Multimodal LLMs (MLLMs), their ability to reason over 3D structures and temporal dynamics remains limited, constrained by weak 4D perception and temporal unders…
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…
Heatmap Regression without Soft-Argmax for Facial Landmark Detection
Chiao-An Yang, Raymond A. Yeh
Facial landmark detection is an important task in computer vision with numerous applications, such as head pose estimation, expression analysis, face swapping, etc. Heatmap regress…
Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts
Chiao-An Yang, Kuan-Chuan Peng, Raymond A. Yeh
Anomaly detection (AD) identifies the defect regions of a given image. Recent works have studied AD, focusing on learning AD without abnormal images, with long-tailed distributed t…
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…
Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention
Haomeng Zhang, Chiao-An Yang, Raymond A. Yeh
Multi-object 3D Grounding involves locating 3D boxes based on a given query phrase from a point cloud. It is a challenging and significant task with numerous applications in visual…
Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time
Chiao-An Yang, Ziwei Liu, Raymond A. Yeh
Subsampling layers play a crucial role in deep nets by discarding a portion of an activation map to reduce its spatial dimensions. This encourages the deep net to learn higher-leve…
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…