Ziyu Guo

point cloud (5) zero-shot learning (4) multimodal learning (4) contrastive learning (3) multi-modal learning (3) few-shot learning (3) 3d vision (3) large language model (3) visual reasoning (2) object detection (2) motion generation (2) masked autoencoder (2) autonomous driving (2) chain-of-thought reasoning (2) question answering (1) attention mechanism (1) self-supervised learning (1) direct preference optimization (1) transfer learning (1) depth estimation (1)