Yuxiang Wei

17

Papers

445

Total Citations

1

Affiliations

Affiliations

Harbin Institute of Technology

Papers (17)

ControlVideo: Training-free Controllable Text-to-video Generation

Improving Image Restoration through Removing Degradations in Textual Representations

ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation

PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis

ACE: Anti-Editing Concept Erasure in Text-to-Image Models

PurpCode: Reasoning for Safer Code Generation

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models

Magicoder: Empowering Code Generation with OSS-Instruct

Retrieval-Based Spatially Adaptive Normalization for Semantic Image Synthesis

Inferring and Leveraging Parts From Object Shape for Improving Semantic Image Synthesis

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation

ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation

Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision

VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models

3752 Decoupled Textual Embeddings for Customized Image Generation

Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks