Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)

• URL: http://arxiv.org/abs/2505.20029v1
• Date: Mon, 26 May 2025 14:18:15 GMT
• Title: Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)
• Authors: Subba Reddy Oota, Akshett Jindal, Ishani Mondal, Khushbu Pahwa, Satya Sai Srinath Namburi, Manish Shrivastava, Maneesh Singh, Bapi S. Raju, Manish Gupta,
• Abstract summary: Transformer-based language models, though not explicitly trained to mimic brain recordings, have demonstrated surprising alignment with brain activity.<n>Recently, a new class of instruction-tuned multimodal LLMs have emerged, showing remarkable zero-shot capabilities in open-ended multimodal vision tasks.<n>We investigate whether MLLMs, when prompted with natural instructions, lead to better brain alignment and effectively capture instruction-specific representations.
• Score: 22.244699182222824
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based language models, though not explicitly trained to mimic brain recordings, have demonstrated surprising alignment with brain activity. Progress in these models-through increased size, instruction-tuning, and multimodality-has led to better representational alignment with neural data. Recently, a new class of instruction-tuned multimodal LLMs (MLLMs) have emerged, showing remarkable zero-shot capabilities in open-ended multimodal vision tasks. However, it is unknown whether MLLMs, when prompted with natural instructions, lead to better brain alignment and effectively capture instruction-specific representations. To address this, we first investigate brain alignment, i.e., measuring the degree of predictivity of neural visual activity using text output response embeddings from MLLMs as participants engage in watching natural scenes. Experiments with 10 different instructions show that MLLMs exhibit significantly better brain alignment than vision-only models and perform comparably to non-instruction-tuned multimodal models like CLIP. We also find that while these MLLMs are effective at generating high-quality responses suitable to the task-specific instructions, not all instructions are relevant for brain alignment. Further, by varying instructions, we make the MLLMs encode instruction-specific visual concepts related to the input image. This analysis shows that MLLMs effectively capture count-related and recognition-related concepts, demonstrating strong alignment with brain activity. Notably, the majority of the explained variance of the brain encoding models is shared between MLLM embeddings of image captioning and other instructions. These results suggest that enhancing MLLMs' ability to capture task-specific information could lead to better differentiation between various types of instructions, and thereby improving their precision in predicting brain responses.

Related papers

• Instruction-Tuned Video-Audio Models Elucidate Functional Specialization in the Brain [25.98830728450583]
  multimodal large language models (MLLMs) exhibit a higher degree of brain alignment compared to unimodal models.<n>We show that instruction-tuned video MLLMs significantly outperform non-instruction-tuned multimodal and unimodal models.<n>Our evaluation of MLLMs for both video and audio tasks using language-guided instructions shows clear disentanglement in task-specific representations from MLLMs.
  arXiv  Detail & Related papers  (2025-06-09T22:48:36Z)
• TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning [54.033346088090674]
  We introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding ability.<n>To fine-tune the model effectively, we generate a high-quality synthetic dataset we call SCOUT.<n>This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process.
  arXiv  Detail & Related papers  (2024-10-14T13:35:47Z)
• LLM4Brain: Training a Large Language Model for Brain Video Understanding [9.294352205183726]
  We introduce an LLM-based approach for reconstructing visual-semantic information from fMRI signals elicited by video stimuli. We employ fine-tuning techniques on an fMRI encoder equipped with adaptors to transform brain responses into latent representations aligned with the video stimuli. In particular, we integrate self-supervised domain adaptation methods to enhance the alignment between visual-semantic information and brain responses.
  arXiv  Detail & Related papers  (2024-09-26T15:57:08Z)
• CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models [68.64605538559312]
  In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives. Inspired by our findings, we propose a measurement to quantitatively evaluate the learning balance. In addition, we introduce an auxiliary loss regularization method to promote updating of the generation distribution of MLLMs.
  arXiv  Detail & Related papers  (2024-07-29T23:18:55Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• Dense Connector for MLLMs [89.50595155217108]
  We introduce the Dense Connector - a plug-and-play vision-language connector that significantly enhances existing MLLMs. Building on this, we also propose the Efficient Dense Connector, which achieves performance comparable to LLaVA-v1.5 with only 25% of the visual tokens. Our model, trained solely on images, showcases remarkable zero-shot capabilities in video understanding as well.
  arXiv  Detail & Related papers  (2024-05-22T16:25:03Z)
• Aligned with LLM: a new multi-modal training paradigm for encoding fMRI activity in visual cortex [4.57590454144072]
  Recently, there has been a surge in the popularity of pre trained large language models (LLMs) This paper proposes a new multi-modal training paradigm, aligning with LLM, encoding fMRI activity in visual cortex.
  arXiv  Detail & Related papers  (2024-01-08T12:30:23Z)
• Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning [67.0609518552321]
  We propose to conduct Machine Vision Therapy which aims to rectify the noisy predictions from vision models. By fine-tuning with the denoised labels, the learning model performance can be boosted in an unsupervised manner.
  arXiv  Detail & Related papers  (2023-12-05T07:29:14Z)
• LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge [58.82222646803248]
  Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. Most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs, leading to insufficient extraction and reasoning of visual knowledge. We propose a dual-Level vIsual knedgeOwl eNhanced Multimodal Large Language Model (LION), which empowers the MLLM by injecting visual knowledge in two levels.
  arXiv  Detail & Related papers  (2023-11-20T15:56:44Z)
• From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models [36.41816380074965]
  We investigate the effectiveness of different vision encoders within Large Language Models (MLLMs) Our findings reveal that the shallow layer features of CLIP offer particular advantages for fine-grained tasks such as grounding and region understanding. We propose a simple yet effective feature merging strategy, named COMM, that integrates CLIP and DINO with Multi-level features Merging.
  arXiv  Detail & Related papers  (2023-10-13T02:41:55Z)
• VideoLLM: Modeling Video Sequence with Large Language Models [70.32832021713864]
  Existing video understanding models are often task-specific and lack a comprehensive capability of handling diverse tasks. We propose a novel framework called VideoLLM that leverages the sequence reasoning capabilities of pre-trained LLMs. VideoLLM incorporates a carefully designed Modality and Semantic Translator, which convert inputs from various modalities into a unified token sequence.
  arXiv  Detail & Related papers  (2023-05-22T17:51:22Z)
• Visual representations in the human brain are aligned with large language models [7.779248296336383]
  We show that large language models (LLMs) are beneficial for modelling the complex visual information extracted by the brain from natural scenes. We then train deep neural network models to transform image inputs into LLM representations.
  arXiv  Detail & Related papers  (2022-09-23T17:34:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.