Jiawei Guo

multimodal large language model (2) visual question answering (2) factual accuracy (1) chain-of-thought reasoning (1) image captioning (1) graph structure (1) instruction tuning (1) content optimization (1) vision language model (1) vision-language model (1) hallucination detection (1) multimodal reasoning (1) data filtering (1) token compression (1) visual token pruning (1) query augmentation (1) large language model (1) generative search engine (1) multimodal instruction tuning (1) answer leakage (1)