Kwan-Yee K. Wong

7

Papers

47

Total Citations

Papers (7)

PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis

DriveGPT4-V2: Harnessing Large Language Model Capabilities for Enhanced Closed-Loop Autonomous Driving

Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers

DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models

Dual-Expert Consistency Model for Efficient and High-Quality Video Generation

ArtiFade: Learning to Generate High-quality Subject from Blemished Images

Affordances-Oriented Planning Using Foundation Models for Continuous Vision-Language Navigation