Luping Liu

diffusion model (2) text-to-audio generation (2) contrastive learning (1) scene understanding (1) object detection (1) preference learning (1) question answering (1) signal-to-noise ratio (1) multimodal learning (1) multi-modal learning (1) visual grounding (1) semantic alignment (1) multitask learning (1) speech enhancement (1) reinforcement learning from human feedback (1) speech synthesis (1) zero-shot learning (1) cross-modal alignment (1) vision-language model (1) representation learning (1)