# Aligned with LLM: a new multi-modal training paradigm for encoding fMRI activity in visual cortex

arXiv: https://arxiv.org/abs/2401.03851 · HTML: https://mlsanity.com/paper/2401.03851/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 24 references that are in the map.
- First posted on arXiv 8 Jan 2024.

## Builds on (most cited first, 4 of 4)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [The Algonauts Project 2023 Challenge: How the Human Brain Makes Sense of Natural Scenes](https://mlsanity.com/paper/2301.03198/) (2023)
- [BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding](https://mlsanity.com/paper/2302.12971/) (2023)

## Built on by (most cited first, 2 of 2)

- [The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective](https://mlsanity.com/paper/2407.08583/) (2024)
- [SABER: A Semantic-Aligned Brain Network Analysis Framework via Multi-scale Hypergraphs](https://mlsanity.com/paper/2607.01901/) (2026)

## Abstract (arXiv)

Recently, there has been a surge in the popularity of pre trained large language models (LLMs) (such as GPT-4), sweeping across the entire Natural Language Processing (NLP) and Computer Vision (CV) communities. These LLMs have demonstrated advanced multi-modal understanding capabilities and showcased strong performance across various benchmarks. The LLM has started to embody traits of artificial general intelligence, which holds vital guidance for enhancing brain-like characteristics within visual encoding models. Hence, This paper proposes a new multi-modal training paradigm, aligning with LLM, for encoding fMRI activity in visual cortex. Based on this paradigm, we trained an encoding model in fMRI data named the LLM-Visual Encoding Model (LLM-VEM). Specifically, we utilize LLM (miniGPT4) to generate descriptive text for all stimulus images, forming a high-quality textual description set. Moreover, we use the pre-trained text encoder (CLIP) to process these detailed descriptions, obtaining the text embedding features. Next, we use the contrast loss function to minimize the distance between the image embedding features and the text embedding features to complete the alignment operation of the stimulus image and text information. With the assistance of the pre-trained LLM, this alignment process facilitates better learning of the visual encoding model, resulting in higher precision. The final experimental results indicate that our training paradigm has significantly aided in enhancing the performance of the visual encoding model.