publications

2025

1. ACM MM

   

   MaXsive: High-Capacity and Robust Training-Free Generative Image Watermarking in Diffusion Models

   Po-Yuan Mao, Cheng-Chang Tsai, and Chun-Shien Lu

   2025
2. ICCV

   

   VSC: Visual Search Compositional Text-to-Image Diffusion Model

   Dat Do Huu, Hyeonu Nam, Po-Yuan Mao, and 1 more author

   arXiv preprint arXiv:2505.01104, 2025
3. WACV Oral

   

   HOPE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts

   Do Huu* Dat, Po-Yuan Mao^*, Tien Hoang Nguyen, and 2 more authors

   In Proceedings of the Winter Conference on Applications of Computer Vision (WACV), Feb 2025

2024

1. Adapting to Covariate Shift in Real-time by Encoding Trees with Motion Equations

   Tham Yik Foong, Heng Zhang, Po-Yuan Mao, and 1 more author

   Feb 2024

2. 

   Breaking Free: How to Hack Safety Guardrails in Black-Box Diffusion Models!

   Shashank Kotyan^*, Po-Yuan Mao^*, Pin-Yu Chen, and 1 more author

   Feb 2024

   HTML

2023

1. Synthetic Shifts to Initial Seed Vector Exposes the Brittle Nature of Latent-Based Diffusion Models

   Po-Yuan Mao, Shashank Kotyan, Tham Yik Foong, and 1 more author

   Feb 2023
2. The Challenges of Image Generation Models in Generating Multi-Component Images

   Tham Yik Foong, Shashank Kotyan, Po-Yuan Mao, and 1 more author

   Feb 2023
3. Neurocomputing

   

   Magnum: Tackling high-dimensional structures with self-organization

   Po-Yuan Mao, Yikfoong Tham, Heng Zhang, and 1 more author

   Neurocomputing, Feb 2023

   Abs

   A big challenge in dealing with real-world problems is scalability. In fact, this is partially the reason behind the success of deep learning over other learning paradigms. Here, we tackle the scalability of a novel learning paradigm proposed in 2021 based solely on self-organizing principles. This paradigm consists of only dynamical equations which self-organize with the input to create attractor-repeller points that are related to the patterns found in data. To achieve scalability for such a system, we propose the Magnum algorithm, which utilizes many self-organizing subsystems (Inertia-SyncMap) each with subsets of the problem’s variables. The main idea is that by merging Inertia-SyncMaps, Magnum builds over time a variable correlation by consensus, capable of accurately predicting the structure of large groups of variables. Experiments show that Magnum surpasses or ties with other unsupervised algorithms in all of the high-dimensional chunking problems, each with distinct types of shapes and structural features. Moreover, Inertia-SyncMap alone outperforms or ties with other unsupervised algorithms in six out of seven basic chunking problems. Thus, this work sheds light on how self-organization learning paradigms can be scaled up to deal with high-dimensional structures and compete with current learning paradigms.