Disentangled representation learning

X Wang, H Chen, Z Wu, W Zhu - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Disentangled Representation Learning (DRL) aims to learn a model capable of identifying
and disentangling the underlying factors hidden in the observable data in representation …

Automated disentangled sequential recommendation with large language models

X Wang, H Chen, Z Pan, Y Zhou, C Guan… - ACM Transactions on …, 2025 - dl.acm.org
Sequential recommendation aims to recommend the next items that a target user may have
interest in based on the user's sequence of past behaviors, which has become a hot …

Diff-privacy: Diffusion-based face privacy protection

X He, M Zhu, D Chen, N Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Privacy protection has become a top priority due to the widespread collection and misuse of
personal data. Anonymization and visual identity information hiding are two crucial tasks in …

Catversion: Concatenating embeddings for diffusion-based text-to-image personalization

R Zhao, M Zhu, S Dong, D Cheng… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
We propose CatVersion, an inversion-based method that learns the personalized concept
through a handful of examples. Subsequently, users can utilize text prompts to generate …

Scenedreamer360: Text-driven 3d-consistent scene generation with panoramic gaussian splatting

W Li, F Cai, Y Mi, Z Yang, W Zuo, X Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Text-driven 3D scene generation has seen significant advancements recently. However,
most existing methods generate single-view images using generative models and then stitch …

Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation

Z Zhang, X Wang, H Chen, H Li, W Zhu - ACM Transactions on …, 2024 - dl.acm.org
Sequential recommendation, leveraging user-item interaction histories to provide
personalized and timely suggestions, has drawn significant research interest recently. With …

Disentangled representation learning with transmitted information bottleneck

Z Dang, M Luo, C Jia, G Dai, J Wang… - … on Circuits and …, 2024 - ieeexplore.ieee.org
Encoding only the task-related information from the raw data, ie, disentangled
representation learning, can greatly contribute to the robustness and generalizability of …

Prior Preserved Text-to-Image Personalization without Image Regularization

Z Wang, O Li, T Wang, L Wei, Y Hao… - … on Circuits and …, 2024 - ieeexplore.ieee.org
The current state-of-the-art text-to-image (T2I) models have found numerous applications,
driven by their ability to produce photorealistic images. Concept learning, as one notable …

CoDi: Contrastive Disentanglement Generative Adversarial Networks for Zero-Shot Sketch-Based 3D Shape Retrieval

M Meng, W Chen, J Liu, J Yu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Sketch-based 3D shape retrieval has attracted increasing attention in recent years. Most
existing methods fail to address the zero-shot scenario, and the few dedicated to zero-shot …

Fast Sampling of Diffusion Models for Accelerated MRI using Dual Manifold Constraints

L Qiao, R Wang, Y Shu, B Li, W Li… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Diffusion models show great potential in solving inverse problems, including MRI
reconstruction. With its unique characteristics, medical imaging demands both efficiency and …