BLIP-2 on Chen Kai Bloghttps://www.chenk.top/en/tags/blip-2/Recent content in BLIP-2 on Chen Kai BlogHugoenThu, 20 Nov 2025 09:00:00 +0000NLP (11): Multimodal Large Language Modelshttps://www.chenk.top/en/nlp/multimodal-nlp/Thu, 20 Nov 2025 09:00:00 +0000https://www.chenk.top/en/nlp/multimodal-nlp/<p>Humans never perceive the world in one channel at a time. We watch a chart while reading the caption, hear a tone of voice while reading a face, glance at a screenshot while debating a bug. Pure-text language models are deaf and blind to all of that. <strong>Multimodal Large Language Models (MLLMs)</strong> close the gap by aligning images, audio, and video into the same representation space the language model already speaks.</p>