Chaowei Xiao

Latest

• PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
• VoxFormer: Sparse voxel transformer for camera-based 3D semantic scene completion
• Prismer: A Vision-Language Model with An Ensemble of Experts
• Test-time prompt tuning for zero-shot generalization in vision-language models
• Diffusion Models for Adversarial Purification
• Understanding The Robustness in Vision Transformers