Re-Imagining Multimodal Instruction Tuning: A Representation View

• URL: http://arxiv.org/abs/2503.00723v3
• Date: Thu, 20 Mar 2025 21:26:06 GMT
• Title: Re-Imagining Multimodal Instruction Tuning: A Representation View
• Authors: Yiyang Liu, James Chenhao Liang, Ruixiang Tang, Yugyung Lee, Majid Rabbani, Sohail Dianat, Raghuveer Rao, Lifu Huang, Dongfang Liu, Qifan Wang, Cheng Han,
• Abstract summary: Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization.<n>As the scale of LMMs continues to grow, fully fine-tuning these models has become highly parameter-intensive.<n>We introduce Multimodal Representation Tuning (MRT), a novel approach that focuses on directly editing semantically rich multimodal representations.
• Score: 43.330347334276965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instruction-following data. However, as the scale of LMMs continues to grow, fully fine-tuning these models has become highly parameter-intensive. Although Parameter-Efficient Fine-Tuning (PEFT) methods have been introduced to reduce the number of tunable parameters, a significant performance gap remains compared to full fine-tuning. Furthermore, existing PEFT approaches are often highly parameterized, making them difficult to interpret and control. In light of this, we introduce Multimodal Representation Tuning (MRT), a novel approach that focuses on directly editing semantically rich multimodal representations to achieve strong performance and provide intuitive control over LMMs. Empirical results show that our method surpasses current state-of-the-art baselines with significant performance gains (e.g., 1580.40 MME score) while requiring substantially fewer tunable parameters (e.g., 0.03% parameters). Additionally, we conduct experiments on editing instrumental tokens within multimodal representations, demonstrating that direct manipulation of these representations enables simple yet effective control over network behavior.

Related papers

• HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding [67.24430397016275]
  We propose a new early-fusion LMM that can fuse multi-modal inputs in the early stage and respond to visual instructions in an auto-regressive manner. The proposed model demonstrates superior performance compared to other LMMs using one transformer and significantly narrows the performance gap with compositional LMMs.
  arXiv  Detail & Related papers  (2025-03-12T06:01:05Z)
• Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models [24.62337386603331]
  Large Multi-modal Models (LMMs) are revolutionizing the way machines interact with the world. To adapt LMMs for downstream tasks, parameter-efficient fine-tuning (PEFT) has gained popularity. This paper focuses on the strengths and weaknesses of each tuning strategy, shifting the focus from the efficiency typically associated with these approaches.
  arXiv  Detail & Related papers  (2024-10-29T07:55:50Z)
• M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning [90.75075886543404]
  Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains. In this work, we introduce a novel Multimodal Prompt Tuning (M$2$PT) approach for efficient instruction tuning of MLLMs.
  arXiv  Detail & Related papers  (2024-09-24T01:40:24Z)
• Intuition-aware Mixture-of-Rank-1-Experts for Parameter Efficient Finetuning [50.73666458313015]
  Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications. MoE has been emerged as a promising solution with its sparse architecture for effective task decoupling. Intuition-MoR1E achieves superior efficiency and 2.15% overall accuracy improvement across 14 public datasets.
  arXiv  Detail & Related papers  (2024-04-13T12:14:58Z)
• Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning [34.49906405191175]
  This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs) tuning LayerNorm suffices to yield strong performance. When benchmarked against other tuning approaches like full parameter finetuning or LoRA, its benefits on efficiency are substantial.
  arXiv  Detail & Related papers  (2023-12-18T18:21:43Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning [55.50908600818483]
  Fine-tuning large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. We propose an Effective and Efficient Visual Prompt Tuning (E2VPT) approach for large-scale transformer-based model adaptation. Our approach outperforms several state-of-the-art baselines on two benchmarks.
  arXiv  Detail & Related papers  (2023-07-25T19:03:21Z)

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.