# MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval

arXiv: https://arxiv.org/abs/2309.01516 · HTML: https://mlsanity.com/paper/2309.01516/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 4 Sep 2023.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)
- [VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks](https://mlsanity.com/paper/2112.06825/) (2021)
- [Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition](https://mlsanity.com/paper/2202.03218/) (2022)
- [An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2107.13530/) (2021)
- [Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2203.16082/) (2022)
- [Parameter-efficient transfer learning of pre-trained Transformer models for speaker verification using adapters](https://mlsanity.com/paper/2210.16032/) (2022)
- [Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis](https://mlsanity.com/paper/2212.00678/) (2022)

## Built on by (most cited first, 9 of 9)

- [Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey](https://mlsanity.com/paper/2402.05391/) (2024)
- [A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks](https://mlsanity.com/paper/2411.06284/) (2024)
- [Re-Imagining Multimodal Instruction Tuning: A Representation View](https://mlsanity.com/paper/2503.00723/) (2025)
- [Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity](https://mlsanity.com/paper/2501.16295/) (2025)
- [CATCH: A Modular Cross-domain Adaptive Template with Hook](https://mlsanity.com/paper/2510.26582/) (2025)
- [Diffusion Augmented Retrieval: A Training-Free Approach to Interactive Text-to-Image Retrieval](https://mlsanity.com/paper/2501.15379/) (2025)
- [Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning](https://mlsanity.com/paper/2403.06289/) (2024)
- [Multi-Point Positional Insertion Tuning for Small Object Detection](https://mlsanity.com/paper/2412.18090/) (2024)
- [RoboEye: Enhancing 2D Robotic Object Identification with Selective 3D Geometric Keypoint Matching](https://mlsanity.com/paper/2509.14966/) (2025)

## Abstract (arXiv)

As Multimodal Large Language Models (MLLMs) grow in size, adapting them to specialized tasks becomes increasingly challenging due to high computational and memory demands. Indeed, traditional fine-tuning methods are costly, due to the need for extensive, task-specific training. While efficient adaptation methods exist that aim to reduce these costs, in practice they suffer from shallow inter-modal alignment, which severely hurts model effectiveness. To tackle these computational challenges and improve inter-modal alignment, we introduce the MultiWay-Adapter (MWA), a novel framework featuring an 'Alignment Enhancer'. This enhancer deepens inter-modal alignment, enabling high transferability with minimal tuning effort. Our experiments show that unlike prior efficient tuning approaches, MWA maintains model effectiveness, while reducing training time by up-to 57%. MWA is also lightweight, increasing model size by only 2-3% (in terms of parameters) for state-of-the-art foundation models like BEiT-3 Large. These results demonstrate that MWA provides an efficient and effective adaptation method for MLLMs, significantly broadening their applicability.