# PixelWorld: How Far Are We from Perceiving Everything as Pixels?

arXiv: https://arxiv.org/abs/2501.19339 · HTML: https://mlsanity.com/paper/2501.19339/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 31 Jan 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 31)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?](https://mlsanity.com/paper/2403.14624/) (2024)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers](https://mlsanity.com/paper/2305.07185/) (2023)
- [Byte Latent Transformer: Patches Scale Better Than Tokens](https://mlsanity.com/paper/2412.09871/) (2024)
- [Improve Vision Language Model Chain-of-thought Reasoning](https://mlsanity.com/paper/2410.16198/) (2024)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [Unifying Multimodal Retrieval via Document Screenshot Embedding](https://mlsanity.com/paper/2406.11251/) (2024)
- [Large Concept Models: Language Modeling in a Sentence Representation Space](https://mlsanity.com/paper/2412.08821/) (2024)
- [Getting the most out of your tokenizer for pre-training and domain adaptation](https://mlsanity.com/paper/2402.01035/) (2024)
- [Language Modelling with Pixels](https://mlsanity.com/paper/2207.06991/) (2022)
- [MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks](https://mlsanity.com/paper/2410.10563/) (2024)
- [TravelAgent: An AI Assistant for Personalized Travel Planning](https://mlsanity.com/paper/2409.08069/) (2024)
- [Tokenization Falling Short: On Subword Robustness in Large Language Models](https://mlsanity.com/paper/2406.11687/) (2024)
- [Improving Language Understanding from Screenshots](https://mlsanity.com/paper/2402.14073/) (2024)
- [Robot Navigation Using Physically Grounded Vision-Language Models in Outdoor Environments](https://mlsanity.com/paper/2409.20445/) (2024)

## Built on by (most cited first, 4 of 4)

- [Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning](https://mlsanity.com/paper/2601.14750/) (2026)
- [Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs](https://mlsanity.com/paper/2603.09095/) (2026)
- [PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.28344/) (2026)
- [Pixelis: Reasoning in Pixels, from Seeing to Acting](https://mlsanity.com/paper/2603.25091/) (2026)

## Abstract (arXiv)

Recent agentic language models increasingly need to interact with real-world environments that contain tightly intertwined visual and textual information, often through raw camera pixels rather than separately processed images and tokenized text. This shift highlights the need for a unified perception paradigm. To investigate this idea, we explore Perceive Everything as Pixels (PEAP) and introduce PixelWorld, a benchmark that renders natural-language, tabular, mathematical, and diagrammatic inputs into a shared pixel space. Experiments across multiple benchmarks show that PEAP achieves comparable performance to token-based approaches on semantic understanding tasks, suggesting that vision transformers can partially capture global textual semantics without explicit tokenization. In contrast, reasoning-intensive tasks such as mathematics and code show notable performance degradation, although Chain-of-Thought prompting helps mitigate this gap by compensating for missing symbolic structure. We further find that when visual and textual information are closely integrated, representing everything as pixels simplifies preprocessing and avoids cross-modal misalignment. PixelWorld thus provides a systematic and practical framework for evaluating unified vision--language models and facilitates further exploration of pixel-based multimodal learning.