Skip to main navigation Skip to search Skip to main content

Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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. This innovative projector also removes the need for manually designing the 2D scan order of original image features when converting them into an input sequence for Mamba LLM. Experimental results across various vision-language understanding benchmarks show that the proposed cross-modal projector enhances Mamba-based multimodal LLMs, boosting both performance and throughput.

Original languageEnglish (US)
Title of host publicationEMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2024
EditorsYaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
PublisherAssociation for Computational Linguistics (ACL)
Pages14158-14167
Number of pages10
ISBN (Electronic)9798891761681
DOIs
StatePublished - 2024
Event2024 Findings of the Association for Computational Linguistics, EMNLP 2024 - Hybrid, Miami, United States
Duration: Nov 12 2024Nov 16 2024

Publication series

NameEMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2024

Conference

Conference2024 Findings of the Association for Computational Linguistics, EMNLP 2024
Country/TerritoryUnited States
CityHybrid, Miami
Period11/12/2411/16/24

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM'. Together they form a unique fingerprint.

Cite this