Zhendong Mao

18

Papers

66

Total Citations

Papers (18)

RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization

RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models

D^2iT: Dynamic Diffusion Transformer for Accurate Image Generation

DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization

LongAnimation: Long Animation Generation with Dynamic Global-Local Memory

ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA

Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection

DreamIdentity: Enhanced Editability for Efficient Face-Identity Preserved Image Generation

Identification of Necessary Semantic Undertakers in the Causal View for Image-Text Matching

1066 Benchmarking Large Language Models on Controllable Generation under Diversified Instructions

Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing

SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation

Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment

Dragin3D: Image Editing by Dragging in 3D Space

A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models

FeedEdit: Text-Based Image Editing with Dynamic Feedback Regulation

Hierarchy-Aware Pseudo Word Learning with Text Adaptation for Zero-Shot Composed Image Retrieval

CustomContrast: A Multilevel Contrastive Perspective for Subject-Driven Text-to-Image Customization