# Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders

arXiv: https://arxiv.org/abs/2507.03262 · HTML: https://mlsanity.com/paper/2507.03262/

## 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 54 of its 71 references that are in the map.
- First posted on arXiv 4 Jul 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, 30 of 54)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [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)
- [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)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (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)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024)
- [PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction](https://mlsanity.com/paper/2410.17247/) (2024)
- [SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models](https://mlsanity.com/paper/2311.07575/) (2023)

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

- [Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback](https://mlsanity.com/paper/2507.20766/) (2025)
- [Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2603.05235/) (2026)
- [Scope: Selective Cross-modal Orchestration of Visual Perception Experts](https://mlsanity.com/paper/2510.12974/) (2025)
- [ViewSparsifier: Killing Redundancy in Multi-View Plant Phenotyping](https://mlsanity.com/paper/2509.08550/) (2025)
- [Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs](https://mlsanity.com/paper/2606.03879/) (2026)

## Abstract (arXiv)

Recent multimodal large language models (MLLMs) increasingly integrate multiple vision encoders to improve performance on various benchmarks, assuming that diverse pretraining objectives yield complementary visual signals. However, we show this assumption often fails in practice. Through systematic encoder masking across representative multi encoder MLLMs, we find that performance typically degrades gracefully, and sometimes even improves, when selected encoders are masked, revealing pervasive encoder redundancy. To quantify this effect, we introduce two principled metrics: the Conditional Utilization Rate (CUR), which measures an encoder s marginal contribution in the presence of others, and the Information Gap (IG), which captures heterogeneity in encoder utility within a model. Using these tools, we observe: (i) strong specialization on tasks like OCR and Chart, where a single encoder can dominate with a CUR greater than 90 percent, (ii) high redundancy on general VQA and knowledge based tasks, where encoders are largely interchangeable, (iii) instances of detrimental encoders with negative CUR. Notably, masking specific encoders can yield up to 16 percent higher accuracy on a specific task category and 3.6 percent overall performance boost compared to the full model.Furthermore, single and dual encoder variants recover over 90 percent of baseline on most non OCR tasks with substantially lower training resources and inference latency. Our analysis challenges the more encoders are better heuristic in MLLMs and provides actionable diagnostics for developing more efficient and effective multimodal architectures.