# Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding

arXiv: https://arxiv.org/abs/2602.01785 · HTML: https://mlsanity.com/paper/2602.01785/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 67 of its 109 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 30 of 67)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis](https://mlsanity.com/paper/1904.01906/) (2019)
- [Large Language Models for Software Engineering: Survey and Open Problems](https://mlsanity.com/paper/2310.03533/) (2023)
- [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024)
- [Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs](https://mlsanity.com/paper/2404.05719/) (2024)
- [Reading Text in the Wild with Convolutional Neural Networks](https://mlsanity.com/paper/1412.1842/) (2014)
- [DocLLM: A layout-aware generative language model for multimodal document understanding](https://mlsanity.com/paper/2401.00908/) (2023)
- [TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes](https://mlsanity.com/paper/1807.01544/) (2018)
- [LongCoder: A Long-Range Pre-trained Language Model for Code Completion](https://mlsanity.com/paper/2306.14893/) (2023)
- [Chargrid: Towards Understanding 2D Documents](https://mlsanity.com/paper/1809.08799/) (2018)

## Built on by (most cited first, 13 of 13)

- [EffiSkill: Agent Skill Based Automated Code Efficiency Optimization](https://mlsanity.com/paper/2603.27850/) (2026)
- [SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring](https://mlsanity.com/paper/2608.09802/) (2026)
- [FastContext: Training Efficient Repository Explorer for Coding Agents](https://mlsanity.com/paper/2606.14066/) (2026)
- [TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering](https://mlsanity.com/paper/2604.03393/) (2026)
- [LLM Agents Can See Code Repositories](https://mlsanity.com/paper/2606.14061/) (2026)
- [ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation](https://mlsanity.com/paper/2604.26923/) (2026)
- [SWE-Pruner Pro: The Coder LLM Already Knows What to Prune](https://mlsanity.com/paper/2607.18213/) (2026)
- [Deep Agentic Search for Repository-Level Code Question Answering: An Empirical Study](https://mlsanity.com/paper/2608.01507/) (2026)
- [ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction](https://mlsanity.com/paper/2604.23813/) (2026)
- [Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text](https://mlsanity.com/paper/2606.09585/) (2026)
- [Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution](https://mlsanity.com/paper/2607.01929/) (2026)
- [CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding](https://mlsanity.com/paper/2607.29637/) (2026)
- [Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations](https://mlsanity.com/paper/2608.09268/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational efficiency has become a critical bottleneck. Currently, these models rely on a text-based paradigm that treats source code as a linear sequence of tokens, which leads to a linear increase in context length and associated computational costs. The rapid advancement of Multimodal LLMs (MLLMs) introduces an opportunity to optimize efficiency by representing source code as rendered images. Unlike text, which is difficult to compress without losing semantic meaning, the image modality is inherently suitable for compression. By adjusting resolution, images can be scaled to a fraction of their original token cost while remaining recognizable to vision-capable models. To explore the feasibility of this approach, we conduct the first systematic study on the effectiveness of MLLMs for code understanding. Our experiments reveal that: (1) MLLMs can effectively understand code with substantial token reduction, achieving up to 8x compression; (2) MLLMs can effectively leverage visual cues such as syntax highlighting, improving code completion performance under 4x compression; and (3) Code-understanding tasks like clone detection exhibit exceptional resilience to visual compression, with some compression ratios even slightly outperforming raw text inputs. Our findings highlight both the potential and current limitations of MLLMs in code understanding, which points out a shift toward image-modality code representation as a pathway to more efficient inference.