Yuyin Zhou

Latest

• What If We Recaption Billions of Web Images with LLaMA-3?
• Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
• FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning
• Masked Autoencoders Enable Efficient Knowledge Distillers
• Can CNNs Be More Robust Than Transformers?