Xingwu Sun

neural network (3) large language model (3) document retrieval (3) pseudo query (2) transformer architecture (2) adversarial attack (2) evaluation benchmark (2) mixture of expert (2) multimodal large language model (2) parameter efficiency (2) multimodal learning (2) visual question answering (2) dense retrieval (2) state space model (2) vision-language model (2) direct preference optimization (1) preference learning (1) catastrophic forgetting (1) hyperparameter optimization (1) contrastive learning (1)