Wuliang Huang
YOU?
Author Swipe
View article: VersaFusion: A Versatile Diffusion-Based Framework for Fine-Grained Image Editing and Enhancement
VersaFusion: A Versatile Diffusion-Based Framework for Fine-Grained Image Editing and Enhancement Open
Text-to-image (T2I) diffusion models have achieved remarkable progress in generating realistic images from textual descriptions. However, ensuring consistent high-quality image generation with complete backgrounds, object appearance, and o…
View article: Aligning Composed Query with Image via Discriminative Perception from Negative Correspondences
Aligning Composed Query with Image via Discriminative Perception from Negative Correspondences Open
The task of composed image retrieval aims to match the multi-modal query composed of a reference image and a modification sentence with the target image. Most current approaches narrow the distances between the composed queries and targets…
View article: Mitigating Pervasive Modality Absence Through Multimodal Generalization and Refinement
Mitigating Pervasive Modality Absence Through Multimodal Generalization and Refinement Open
The performance of multimodal models often deteriorates when modality absence occurs. The absence disrupts the learned inter-modal correlations, resulting in biased multimodal representations. This challenge is especially pronounced when t…
View article: Semantic Distillation from Neighborhood for Composed Image Retrieval
Semantic Distillation from Neighborhood for Composed Image Retrieval Open
View article: FedEYE: A scalable and flexible end-to-end federated learning platform for ophthalmology
FedEYE: A scalable and flexible end-to-end federated learning platform for ophthalmology Open
Data-driven machine learning, as a promising approach, possesses the capability to build high-quality, exact, and robust models from ophthalmic medical data. Ophthalmic medical data, however, presently exist across disparate data silos wit…
View article: UbiMeta: A Ubiquitous Operating System Model for Metaverse
UbiMeta: A Ubiquitous Operating System Model for Metaverse Open
The metaverse signifies the amalgamation of virtual and tangible realms through human-computer interaction. The seamless integration of human, cyber, and environments within ubiquitous computing plays a pivotal role in fully harnessing the…
View article: Differentially Private Pre-Trained Model Fusion using Decentralized Federated Graph Matching
Differentially Private Pre-Trained Model Fusion using Decentralized Federated Graph Matching Open
Model fusion is becoming a crucial component in the context of model-as-a-service scenarios, enabling the delivery of high-quality model services to local users. However, this approach introduces privacy risks and imposes certain limitatio…
View article: CellPolaris: Decoding Cell Fate through Generalization Transfer Learning of Gene Regulatory Networks
CellPolaris: Decoding Cell Fate through Generalization Transfer Learning of Gene Regulatory Networks Open
Cell fate changes are determined by gene regulatory network (GRN), a sophisticated system regulating gene expression in precise spatial and temporal patterns. However, existing methods for reconstructing GRNs suffer from inherent limitatio…
View article: GJFusion: A Channel-Level Correlation Construction Method for Multimodal Physiological Signal Fusion
GJFusion: A Channel-Level Correlation Construction Method for Multimodal Physiological Signal Fusion Open
Physiological signal based ubiquitous computing has garnered significant attention. However, the heterogeneity among multimodal physiological signals poses a critical challenge to practical applications. To traverse this heterogeneity gap,…
View article: FedBone: Towards Large-Scale Federated Multi-Task Learning
FedBone: Towards Large-Scale Federated Multi-Task Learning Open
Heterogeneous federated multi-task learning (HFMTL) is a federated learning technique that combines heterogeneous tasks of different clients to achieve more accurate, comprehensive predictions. In real-world applications, visual and natura…