# Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion

arXiv: https://arxiv.org/abs/2412.01289 · HTML: https://mlsanity.com/paper/2412.01289/

## Key facts

- Cited by 5 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 42 of its 50 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## 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 42)

- [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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (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)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning](https://mlsanity.com/paper/2306.14565/) (2023)
- [Dataless Knowledge Fusion by Merging Weights of Language Models](https://mlsanity.com/paper/2212.09849/) (2022)
- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding](https://mlsanity.com/paper/2306.17107/) (2023)

## Built on by (most cited first, 5 of 5)

- [OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging](https://mlsanity.com/paper/2505.19892/) (2025)
- [Closed-Form Spectral Regularization for Multi-Task Model Merging](https://mlsanity.com/paper/2606.07289/) (2026)
- [PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging](https://mlsanity.com/paper/2604.22823/) (2026)
- [VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning](https://mlsanity.com/paper/2509.25151/) (2025)
- [SSAM: Singular Subspace Alignment for Merging Multimodal Large Language Models](https://mlsanity.com/paper/2603.21584/) (2026)

## Abstract (arXiv)

Multimodal LLMs (MLLMs) equip language models with visual capabilities by aligning vision encoders with language models. Existing methods to enhance the visual perception of MLLMs often involve designing more powerful vision encoders, which requires exploring a vast design space and re-aligning each potential encoder with the language model, resulting in prohibitively high training costs. In this paper, we introduce VisionFuse, a novel integration framework that efficiently utilizes multiple vision encoders from off-the-shelf MLLMs to enhance visual perception without requiring additional training. Our approach is motivated by the observation that different MLLMs tend to focus on distinct regions given the same query and image. Moreover, we find that the feature distributions of vision encoders within an MLLM family, a group of MLLMs sharing the same pretrained LLM, are highly aligned. Building on these insights, VisionFuse enriches the visual context by concatenating the tokens generated by the vision encoders of selected MLLMs within a family. By merging the parameters of language models from these MLLMs, VisionFuse allows a single language model to align with various vision encoders, significantly reducing deployment overhead. We conduct comprehensive evaluations across multiple multimodal benchmarks using various MLLM combinations, demonstrating substantial improvements in multimodal tasks. Notably, when integrating MiniGemini-8B and SLIME-8B, VisionFuse achieves an average performance increase of over 4%.