Shengyu Zhang

Digital Humanities (1)

multimodal learning (4) recommendation system (4) video understanding (4) video grounding (3) recommender system (3) large language model (3) multimodal large language model (3) graphical user interface (2) diffusion model (2) active learning (2) model merging (2) weakly-supervised learning (2) task automation (2) contrastive learning (2) causal inference (2) representation learning (2) self-supervised learning (2) knowledge distillation (2) reinforcement learning (2) online algorithm (2)