English

LLM4Brain: Training a Large Language Model for Brain Video Understanding

Computer Vision and Pattern Recognition 2024-09-27 v1 Human-Computer Interaction

Abstract

Decoding visual-semantic information from brain signals, such as functional MRI (fMRI), across different subjects poses significant challenges, including low signal-to-noise ratio, limited data availability, and cross-subject variability. Recent advancements in large language models (LLMs) show remarkable effectiveness in processing multimodal information. In this study, we introduce an LLM-based approach for reconstructing visual-semantic information from fMRI signals elicited by video stimuli. Specifically, we employ fine-tuning techniques on an fMRI encoder equipped with adaptors to transform brain responses into latent representations aligned with the video stimuli. Subsequently, these representations are mapped to textual modality by LLM. In particular, we integrate self-supervised domain adaptation methods to enhance the alignment between visual-semantic information and brain responses. Our proposed method achieves good results using various quantitative semantic metrics, while yielding similarity with ground-truth information.

Keywords

Cite

@article{arxiv.2409.17987,
  title  = {LLM4Brain: Training a Large Language Model for Brain Video Understanding},
  author = {Ruizhe Zheng and Lichao Sun},
  journal= {arXiv preprint arXiv:2409.17987},
  year   = {2024}
}

Comments

ECCV2024 Workshop

R2 v1 2026-06-28T18:58:21.138Z