SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.13600 · 2024

VL-Mamba: Exploring State Space Models for Multimodal Learning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

Multimodal large language models (MLLMs) have attracted widespread interest and have rich applications. However, the inherent attention mechanism in its Transformer structure requires quadratic complexity and results in expensive computational overhead. Therefore, in this work, we propose VL-Mamba, a multimodal large language model based on state space models, which have been shown to have great potential for long-sequence modeling with fast inference and linear scaling in sequence length. Specifically, we first replace the transformer-based backbone language model such as LLama or Vicuna with the pre-trained Mamba language model. Then, we empirically explore how to effectively apply the 2D vision selective scan mechanism for multimodal learning and the combinations of different vision encoders and variants of pretrained Mamba language models. The extensive experiments on diverse multimodal benchmarks with competitive performance show the effectiveness of our proposed VL-Mamba and demonstrate the great potential of applying state space models for multimodal learning tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.13600")
get_code_for_paper("2403.13600")
have("2403.13600")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.13600.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.13600.svg)](https://syntology.ai/paper/2403.13600)

Connect an agent — have() is free.