AI RESEARCH
Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM
arXiv CS.CL
•
ArXi:2606.04719v1 Announce Type: new The Transformer's quadratic complexity with input length imposes an unsustainable computational load on large language models (LLMs). In contrast, the Selective Scan Structured State-Space Model, or Mamba, addresses this computational challenge effectively. This paper explores a query-based cross-modal projector designed to bolster Mamba's efficiency for vision-language modeling by compressing visual tokens based on input through the cross-attention mechanism.