Haoyu Cao

multimodal learning (3) multimodal large language model (2) visual document understanding (2) multi-modal learning (2) generative model (2) text generation (1) speech processing (1) reinforcement learning (1) document information extraction (1) embedding learning (1) wavelet transform (1) instruction tuning (1) model pruning (1) bayesian optimization (1) vision-language model (1) document understanding (1) diffusion model (1) curriculum learning (1) embedding alignment (1) contrastive learning (1)