Donghong Han

reinforcement learning (1) catastrophic forgetting (1) dialogue generation (1) response generation (1) multimodal learning (1) model merging (1) parameter-efficient fine-tuning (1) low-rank adaptation (1) mixture of expert (1) vision-language model (1) model efficiency (1) emotional support conversation (1) visual token pruning (1) large language model (1) strategy planning (1) attention redirection (1)