Yongxin Zhu

text generation (3) large language model (3) diffusion model (3) image generation (2) self-supervised learning (2) vector quantization (2) multimodal learning (2) multi-modal learning (2) natural language processing (1) speech processing (1) embedding space (1) named entity recognition (1) continual learning (1) grammatical error correction (1) cross-modal learning (1) visual question answering (1) text representation (1) incremental learning (1) sentiment classification (1) object detection (1)