4 citations · 7 across the 5 of their papers we have counts for
6 papers
D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders
Xinyue Xu, Jiahao Zhang, Lijie Hu +2
Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be used to control generation. We…
Concept-Based Unsupervised Domain Adaptation
Xinyue Xu, Yueying Hu, Hui Tang +4
Concept Bottleneck Models (CBMs) enhance interpretability by explaining predictions through human-understandable concepts but typically assume that training and test data share the…
Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
Xinyue Xu, Yi Qin, Lu Mi +2
Existing methods, such as concept bottleneck models (CBMs), have been successful in providing concept-based interpretations for black-box deep learning models. They typically work…
Dynamic Data Augmentation via MCTS for Prostate MRI Segmentation
Xinyue Xu, Yuhan Hsi, Haonan Wang +1
Medical image data are often limited due to the expensive acquisition and annotation process. Hence, training a deep-learning model with only raw data can easily lead to overfittin…
Reliable and Efficient Evaluation of Adversarial Robustness for Deep Hashing-Based Retrieval
Xunguang Wang, Jiawang Bai, Xinyue Xu +1
Deep hashing has been extensively applied to massive image retrieval due to its efficiency and effectiveness. Recently, several adversarial attacks have been presented to reveal th…
Subgraph Frequency Distribution Estimation using Graph Neural Networks
Zhongren Chen, Xinyue Xu, Shengyi Jiang +2
Small subgraphs (graphlets) are important features to describe fundamental units of a large network. The calculation of the subgraph frequency distributions has a wide application…