Zeyi Sun

vision-language model (3) multimodal large language model (2) multimodal learning (2) few-shot learning (1) policy optimization (1) object detection (1) in-context learning (1) information retrieval (1) point cloud (1) synthetic data generation (1) learning to rank (1) view consistency (1) generative model (1) foundation model (1) pre-trained model (1) 3d generation (1) controllable generation (1) visual prompt (1) material generation (1) auto-regressive model (1)