# Explore How to Inject Beneficial Noise in MLLMs

arXiv: https://arxiv.org/abs/2511.12917 · HTML: https://mlsanity.com/paper/2511.12917/

## Key facts

- Cited by 10 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 29 of its 40 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## 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, 29 of 29)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models](https://mlsanity.com/paper/2407.11691/) (2024)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [Visual Adversarial Examples Jailbreak Aligned Large Language Models](https://mlsanity.com/paper/2306.13213/) (2023)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [Variational Positive-incentive Noise: How Noise Benefits Models](https://mlsanity.com/paper/2306.07651/) (2023)
- [Enhance Vision-Language Alignment with Noise](https://mlsanity.com/paper/2412.10817/) (2024)
- [Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise](https://mlsanity.com/paper/2408.09929/) (2024)
- [Learn Beneficial Noise as Graph Augmentation](https://mlsanity.com/paper/2505.19024/) (2025)
- [NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering](https://mlsanity.com/paper/2503.07076/) (2025)
- [Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attacks](https://mlsanity.com/paper/2503.08269/) (2025)
- [Object-AVEdit: An Object-level Audio-Visual Editing Model](https://mlsanity.com/paper/2510.00050/) (2025)

## Built on by (most cited first, 10 of 10)

- [Enhancing Neural Video Compression of Static Scenes with Positive-Incentive Noise](https://mlsanity.com/paper/2603.06095/) (2026)
- [GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning](https://mlsanity.com/paper/2511.15256/) (2025)
- [ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models](https://mlsanity.com/paper/2512.14099/) (2025)
- [Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation](https://mlsanity.com/paper/2605.22060/) (2026)
- [Multi-Intent Spoken Language Understanding: Methods, Trends, and Challenges](https://mlsanity.com/paper/2512.11258/) (2025)
- [Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models](https://mlsanity.com/paper/2606.30168/) (2026)
- [Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2607.17593/) (2026)
- [Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor Learning](https://mlsanity.com/paper/2608.01635/) (2026)
- [Representation Learning in Diffusion and Flow-based Model: An Application Aspect](https://mlsanity.com/paper/2608.24068/) (2026)
- [On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data](https://mlsanity.com/paper/2609.10321/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have played an increasingly important role in multimodal intelligence. However, the existing fine-tuning methods often ignore cross-modal heterogeneity, limiting their full potential. In this work, we propose a novel fine-tuning strategy by injecting beneficial random noise, which outperforms previous methods and even surpasses full fine-tuning, with minimal additional parameters. The proposed Multimodal Noise Generator (MuNG) enables efficient modality fine-tuning by injecting customized noise into the frozen MLLMs. Specifically, we reformulate the reasoning process of MLLMs from a variational inference perspective, upon which we design a multimodal noise generator that dynamically analyzes cross-modal relationships in image-text pairs to generate task-adaptive beneficial noise. Injecting this type of noise into the MLLMs effectively suppresses irrelevant semantic components, leading to significantly improved cross-modal representation alignment and enhanced performance on downstream tasks. Experiments on two mainstream MLLMs, QwenVL and LLaVA, demonstrate that our method surpasses full-parameter fine-tuning and other existing fine-tuning approaches, while requiring adjustments to only about 1~2% additional parameters. The relevant code is uploaded in the supplementary.