# Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs

arXiv: https://arxiv.org/abs/2510.18279 · HTML: https://mlsanity.com/paper/2510.18279/

## Key facts

- Cited by 8 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 20 of its 35 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## 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, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack](https://mlsanity.com/paper/2406.10149/) (2024)
- [xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token](https://mlsanity.com/paper/2405.13792/) (2024)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [SLM: Bridge the thin gap between speech and text foundation models](https://mlsanity.com/paper/2310.00230/) (2023)
- [Characterizing Prompt Compression Methods for Long Context Inference](https://mlsanity.com/paper/2407.08892/) (2024)
- [Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding](https://mlsanity.com/paper/2412.06474/) (2024)
- [RefreshKV: Updating Small KV Cache During Long-form Generation](https://mlsanity.com/paper/2411.05787/) (2024)
- [From Text to Pixel: Advancing Long-Context Understanding in MLLMs](https://mlsanity.com/paper/2405.14213/) (2024)
- [Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression](https://mlsanity.com/paper/2408.15491/) (2024)
- [Context-Efficient Retrieval with Factual Decomposition](https://mlsanity.com/paper/2503.19574/) (2025)

## Built on by (most cited first, 8 of 8)

- [VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?](https://mlsanity.com/paper/2512.15649/) (2025)
- [VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?](https://mlsanity.com/paper/2602.04802/) (2026)
- [When Text-as-Vision Meets Semantic IDs in Generative Recommendation: An Empirical Study](https://mlsanity.com/paper/2601.14697/) (2026)
- [Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression](https://mlsanity.com/paper/2608.02109/) (2026)
- [Global Context Compression with Interleaved Vision-Text Transformation](https://mlsanity.com/paper/2601.10378/) (2026)
- [Token-Efficient Multimodal Reasoning via Image Prompt Packaging](https://mlsanity.com/paper/2604.02492/) (2026)
- [LoMo: Local Modality Substitution for Deeper Vision-Language Fusion](https://mlsanity.com/paper/2605.30265/) (2026)
- [Dual-Latent Memory Routing for Vision-Language Reasoning](https://mlsanity.com/paper/2609.05539/) (2026)

## Abstract (arXiv)

Large language models (LLMs) and their multimodal variants can now process visual inputs, including images of text. This raises an intriguing question: can we compress textual inputs by feeding them as images to reduce token usage while preserving performance? In this paper, we show that visual text representations are a practical and surprisingly effective form of input compression for decoder LLMs. We exploit the idea of rendering long text inputs as a single image and provide it directly to the model. This leads to dramatically reduced number of decoder tokens required, offering a new form of input compression. Through experiments on two distinct benchmarks RULER (long-context retrieval) and CNN/DailyMail (document summarization) we demonstrate that this text-as-image method yields substantial token savings (often nearly half) without degrading task performance.