# Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning

arXiv: https://arxiv.org/abs/2312.11420 · HTML: https://mlsanity.com/paper/2312.11420/

## Key facts

- Cited by 64 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 37 of its 44 references that are in the map.
- First posted on arXiv 18 Dec 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, 30 of 37)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [PandaGPT: One Model To Instruction-Follow Them All](https://mlsanity.com/paper/2305.16355/) (2023)

## Built on by (most cited first, 30 of 64)

- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning](https://mlsanity.com/paper/2406.12742/) (2024)
- [A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine](https://mlsanity.com/paper/2405.08603/) (2024)
- [Parameter-Efficient Fine-Tuning for Foundation Models](https://mlsanity.com/paper/2501.13787/) (2025)
- [HRP: Human Affordances for Robotic Pre-Training](https://mlsanity.com/paper/2407.18911/) (2024)
- [ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data](https://mlsanity.com/paper/2411.15004/) (2024)
- [How Far Are We From AGI: Are LLMs All We Need?](https://mlsanity.com/paper/2405.10313/) (2024)
- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://mlsanity.com/paper/2504.03151/) (2025)
- [OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning](https://mlsanity.com/paper/2505.04601/) (2025)
- [PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization](https://mlsanity.com/paper/2409.17137/) (2024)
- [ReDi: Rectified Discrete Flow](https://mlsanity.com/paper/2507.15897/) (2025)
- [Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization](https://mlsanity.com/paper/2405.15861/) (2024)
- [ASPS: Augmented Segment Anything Model for Polyp Segmentation](https://mlsanity.com/paper/2407.00718/) (2024)
- [Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models](https://mlsanity.com/paper/2404.16385/) (2024)
- [textttBATCLIP: Bimodal Online Test-Time Adaptation for CLIP](https://mlsanity.com/paper/2412.02837/) (2024)
- [Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency](https://mlsanity.com/paper/2506.10178/) (2025)
- [Beyond LoRA: Exploring Efficient Fine-Tuning Techniques for Time Series Foundational Models](https://mlsanity.com/paper/2409.11302/) (2024)
- [Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection](https://mlsanity.com/paper/2503.09493/) (2025)
- [Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2503.16585/) (2025)
- [DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation](https://mlsanity.com/paper/2503.18225/) (2025)
- [RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates](https://mlsanity.com/paper/2410.10075/) (2024)
- [Understanding Why Large Language Models Can Be Ineffective in Time Series Analysis: The Impact of Modality Alignment](https://mlsanity.com/paper/2410.12326/) (2024)
- [PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2411.19335/) (2024)
- [VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection](https://mlsanity.com/paper/2505.02331/) (2025)
- [PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark](https://mlsanity.com/paper/2511.21285/) (2025)
- [Efficient Open Set Single Image Test Time Adaptation of Vision Language Models](https://mlsanity.com/paper/2406.00481/) (2024)
- [ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models](https://mlsanity.com/paper/2410.09637/) (2024)
- [AERO: Entropy-Guided Framework for Private LLM Inference](https://mlsanity.com/paper/2410.13060/) (2024)
- [Exploiting Mixture-of-Experts Redundancy Unlocks Multimodal Generative Abilities](https://mlsanity.com/paper/2503.22517/) (2025)
- [Segment Any Crack: Deep Semantic Segmentation Adaptation for Crack Detection](https://mlsanity.com/paper/2504.14138/) (2025)

## Abstract (arXiv)

This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text understanding to embracing multiple modalities, we intriguingly note that, within each attention block, tuning LayerNorm suffices to yield strong performance. Moreover, when benchmarked against other tuning approaches like full parameter finetuning or LoRA, its benefits on efficiency are substantial. For example, when compared to LoRA on a 13B model scale, performance can be enhanced by an average of over 20% across five multi-modal tasks, and meanwhile, results in a significant reduction of trainable parameters by 41.9% and a decrease in GPU memory usage by 17.6%. On top of this LayerNorm strategy, we showcase that selectively tuning only with conversational data can improve efficiency further. Beyond these empirical outcomes, we provide a comprehensive analysis to explore the role of LayerNorm in adapting LLMs to the multi-modal domain and improving the expressive power of the model.