# M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension

arXiv: https://arxiv.org/abs/2407.01131 · HTML: https://mlsanity.com/paper/2407.01131/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 53 of its 74 references that are in the map.
- First posted on arXiv 1 Jul 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [Modeling Context Between Objects for Referring Expression Understanding](https://mlsanity.com/paper/1608.00525/) (2016)
- [LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning](https://mlsanity.com/paper/2206.06522/) (2022)
- [A Fast and Accurate One-Stage Approach to Visual Grounding](https://mlsanity.com/paper/1908.06354/) (2019)
- [Language as Queries for Referring Video Object Segmentation](https://mlsanity.com/paper/2201.00487/) (2022)
- [Learning to Assemble Neural Module Tree Networks for Visual Grounding](https://mlsanity.com/paper/1812.03299/) (2018)
- [SeqTR: A Simple yet Universal Network for Visual Grounding](https://mlsanity.com/paper/2203.16265/) (2022)
- [Improving One-stage Visual Grounding by Recursive Sub-query Construction](https://mlsanity.com/paper/2008.01059/) (2020)
- [FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer](https://mlsanity.com/paper/2212.03145/) (2022)
- [A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension](https://mlsanity.com/paper/1909.07072/) (2019)
- [Learning to Compose and Reason with Language Tree Structures for Visual Grounding](https://mlsanity.com/paper/1906.01784/) (2019)
- [TubeDETR: Spatio-Temporal Video Grounding with Transformers](https://mlsanity.com/paper/2203.16434/) (2022)

## Built on by (most cited first, 11 of 11)

- [A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks](https://mlsanity.com/paper/2411.06284/) (2024)
- [Variation-aware Vision Token Dropping for Faster Large Vision-Language Models](https://mlsanity.com/paper/2509.01552/) (2025)
- [Twin Co-Adaptive Dialogue for Progressive Image Generation](https://mlsanity.com/paper/2504.14868/) (2025)
- [ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2408.06747/) (2024)
- [SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding](https://mlsanity.com/paper/2502.16786/) (2025)
- [TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning](https://mlsanity.com/paper/2507.22872/) (2025)
- [Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models](https://mlsanity.com/paper/2503.12149/) (2025)
- [DMPT: Decoupled Modality-aware Prompt Tuning for Multi-modal Object Re-identification](https://mlsanity.com/paper/2504.10985/) (2025)
- [TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation](https://mlsanity.com/paper/2503.17669/) (2025)
- [BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding](https://mlsanity.com/paper/2601.01526/) (2026)
- [Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation](https://mlsanity.com/paper/2509.19733/) (2025)

## Abstract (arXiv)

Referring expression comprehension (REC) is a vision-language task to locate a target object in an image based on a language expression. Fully fine-tuning general-purpose pre-trained vision-language foundation models for REC yields impressive performance but becomes increasingly costly. Parameter-efficient transfer learning (PETL) methods have shown strong performance with fewer tunable parameters. However, directly applying PETL to REC faces two challenges: (1) insufficient multi-modal interaction between pre-trained vision-language foundation models, and (2) high GPU memory usage due to gradients passing through the heavy vision-language foundation models. To this end, we present M2IST: Multi-Modal Interactive Side-Tuning with M3ISAs: Mixture of Multi-Modal Interactive Side-Adapters. During fine-tuning, we fix the pre-trained uni-modal encoders and update M3ISAs to enable efficient vision-language alignment for REC. Empirical results reveal that M2IST achieves better performance-efficiency trade-off than full fine-tuning and other PETL methods, requiring only 2.11% tunable parameters, 39.61% GPU memory, and 63.46% training time while maintaining competitive performance. Our code is released at https://github.com/xuyang-liu16/M2IST.