MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model

Understand

Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs).

• However, its internal mechanisms have yet to be explored.
• Inspired by multilingual research, we identify domain-specific neurons in multimodal large language models.
• Specifically, we investigate the distribution of domain-specific neurons and the mechanism of how MLLMs process features from diverse domains.