# LM4LV: A Frozen Large Language Model for Low-level Vision Tasks

arXiv: https://arxiv.org/abs/2405.15734 · HTML: https://mlsanity.com/paper/2405.15734/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2024.

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

- [UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent](https://mlsanity.com/paper/2501.18867/) (2025)
- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training](https://mlsanity.com/paper/2509.26625/) (2025)
- [Large Language Model for Lossless Image Compression with Visual Prompts](https://mlsanity.com/paper/2502.16163/) (2025)
- [Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers](https://mlsanity.com/paper/2511.13945/) (2025)
- [HazeCLIP: Towards Language Guided Real-World Image Dehazing](https://mlsanity.com/paper/2407.13719/) (2024)
- [LossAgent: Towards Any Optimization Objectives for Image Processing with LLM Agents](https://mlsanity.com/paper/2412.04090/) (2024)
- [Improving Generalization of Language-Conditioned Robot Manipulation](https://mlsanity.com/paper/2508.02405/) (2025)
- [S2LM: Towards Semantic Steganography via Large Language Models](https://mlsanity.com/paper/2511.05319/) (2025)
- [VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought](https://mlsanity.com/paper/2603.22998/) (2026)
- [Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learning](https://mlsanity.com/paper/2605.29577/) (2026)
- [Language-Assisted Super-Resolution from Real-World Low-Resolution Patches](https://mlsanity.com/paper/2606.31363/) (2026)
- [Procedural Core: A Compact Recurrent Initialization for Vision Transformers](https://mlsanity.com/paper/2609.37631/) (2026)

## Abstract (arXiv)

The success of large language models (LLMs) has fostered a new research trend of multi-modality large language models (MLLMs), which changes the paradigm of various fields in computer vision. Though MLLMs have shown promising results in numerous high-level vision and vision-language tasks such as VQA and text-to-image, no works have demonstrated how low-level vision tasks can benefit from MLLMs. We find that most current MLLMs are blind to low-level features due to their design of vision modules, thus are inherently incapable for solving low-level vision tasks. In this work, we purpose LM4LV, a framework that enables a FROZEN LLM to solve a range of low-level vision tasks without any multi-modal data or prior. This showcases the LLM's strong potential in low-level vision and bridges the gap between MLLMs and low-level vision tasks. We hope this work can inspire new perspectives on LLMs and deeper understanding of their mechanisms. Code is available at https://github.com/bytetriper/LM4LV.