# Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See

arXiv: https://arxiv.org/abs/2410.06169 · HTML: https://mlsanity.com/paper/2410.06169/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 53 of its 60 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [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)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [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)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [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)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (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)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [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)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)

## Built on by (most cited first, 23 of 23)

- [AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning](https://mlsanity.com/paper/2412.03248/) (2024)
- [Efficient Multi-modal Large Language Models via Progressive Consistency Distillation](https://mlsanity.com/paper/2510.00515/) (2025)
- [VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs](https://mlsanity.com/paper/2510.17205/) (2025)
- [Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models](https://mlsanity.com/paper/2503.14075/) (2025)
- [Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models](https://mlsanity.com/paper/2503.11519/) (2025)
- [IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning](https://mlsanity.com/paper/2602.03060/) (2026)
- [Multimodal LLMs as Customized Reward Models for Text-to-Image Generation](https://mlsanity.com/paper/2507.21391/) (2025)
- [ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention](https://mlsanity.com/paper/2602.07574/) (2026)
- [Rethinking Chain-of-Thought Reasoning for Videos](https://mlsanity.com/paper/2512.09616/) (2025)
- [EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling](https://mlsanity.com/paper/2604.17087/) (2026)
- [Reallocating Attention Across Layers to Reduce Multimodal Hallucination](https://mlsanity.com/paper/2510.10285/) (2025)
- [CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs](https://mlsanity.com/paper/2502.14882/) (2025)
- [Learning Compact Vision Tokens for Efficient Large Multimodal Models](https://mlsanity.com/paper/2506.07138/) (2025)
- [METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models](https://mlsanity.com/paper/2507.20842/) (2025)
- [Towards Efficient VLMs: Information-Theoretic Driven Compression via Adaptive Structural Pruning](https://mlsanity.com/paper/2511.19518/) (2025)
- [CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models](https://mlsanity.com/paper/2602.00247/) (2026)
- [MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs](https://mlsanity.com/paper/2610.01434/) (2026)
- [Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts](https://mlsanity.com/paper/2411.13909/) (2024)
- [It Takes a Good Model to Train a Good Model: Generalized Gaussian Priors for Optimized LLMs](https://mlsanity.com/paper/2506.00486/) (2025)
- [LOP: Learning Optimal Pruning for Efficient On-Demand MLLMs Scaling](https://mlsanity.com/paper/2506.12826/) (2025)
- [Vision Token Masking Alone Cannot Prevent PHI Leakage in Medical Document OCR: A Systematic Evaluation](https://mlsanity.com/paper/2511.18272/) (2025)
- [Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models](https://mlsanity.com/paper/2609.32808/) (2026)
- [GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs](https://mlsanity.com/paper/2610.13035/) (2026)

## Abstract (arXiv)

By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks, leveraging the robust architectures of Large Language Models (LLMs). However, as token counts grow, the quadratic scaling of computation in LLMs introduces a significant efficiency bottleneck, impeding further scalability. Although recent approaches have explored pruning visual tokens or employing lighter LLM architectures, the computational overhead from an increasing number of visual tokens remains a substantial challenge. In this study, we investigate the redundancy in visual computation at both the parameter and computational pattern levels within LLaVA, a representative MLLM, and introduce a suite of streamlined strategies to enhance efficiency. These include neighbor-aware visual token attention, pruning of inactive visual attention heads, and selective layer dropping for visual computations. By implementing these strategies in LLaVA, we achieve a reduction in computational demands of 88% while maintaining model performance across key benchmarks. Additionally, we validate the existence of visual computational redundancy in other MLLMs, such as Qwen2-VL-7B and InternVL-2.0-4B/8B/26B. These results present a novel pathway for MLLMs to handle dense visual tokens with minimal computational costs. Code and model checkpoints will be released to support further research.