Yunhong Wang

ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving

EmboMatrix: A Scalable Training-Ground for Embodied Decision-Making

DDAE++: Enhancing Diffusion Models Towards Unified Generative and Discriminative Learning

Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction

Text-Guided Visual Prompt Tuning for Vision-Language Models

Temporal Distribution-aware Quantization for Diffusion Models

CLIP-LAD: Unleash the Potential of CLIP for Few-shot Logical Anomaly Detection