# Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need

arXiv: https://arxiv.org/abs/2411.12448 · HTML: https://mlsanity.com/paper/2411.12448/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 19 Nov 2024.

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications](https://mlsanity.com/paper/1701.05517/) (2017)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models](https://mlsanity.com/paper/2310.08659/) (2023)
- [Tokenizer Choice For LLM Training: Negligible or Crucial?](https://mlsanity.com/paper/2310.08754/) (2023)
- [Practical Full Resolution Learned Lossless Image Compression](https://mlsanity.com/paper/1811.12817/) (2018)
- [Compression Represents Intelligence Linearly](https://mlsanity.com/paper/2404.09937/) (2024)
- [Learning Better Lossless Compression Using Lossy Compression](https://mlsanity.com/paper/2003.10184/) (2020)
- [Learning Universal Predictors](https://mlsanity.com/paper/2401.14953/) (2024)
- [iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression](https://mlsanity.com/paper/2103.16211/) (2021)
- [iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder](https://mlsanity.com/paper/2111.00965/) (2021)
- [Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression](https://mlsanity.com/paper/2209.04847/) (2022)
- [Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data](https://mlsanity.com/paper/2410.05078/) (2024)
- [SimNP: Learning Self-Similarity Priors Between Neural Points](https://mlsanity.com/paper/2309.03809/) (2023)
- [Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs](https://mlsanity.com/paper/2409.10033/) (2024)
- [Learned Lossless Image Compression Through Interpolation With Low Complexity](https://mlsanity.com/paper/2212.13243/) (2022)
- [Considering Image Information and Self-similarity: A Compositional Denoising Network](https://mlsanity.com/paper/2209.06417/) (2022)

## Built on by (most cited first, 10 of 10)

- [DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor](https://mlsanity.com/paper/2505.16256/) (2025)
- [Scaling Learned Image Compression Models up to 1 Billion](https://mlsanity.com/paper/2508.09075/) (2025)
- [Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification](https://mlsanity.com/paper/2601.20742/) (2026)
- [TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile Data](https://mlsanity.com/paper/2602.09893/) (2026)
- [OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data](https://mlsanity.com/paper/2602.22286/) (2026)
- [Adapting Diffusion Language Models for Lossless Pixel-Level Image Transmission](https://mlsanity.com/paper/2606.06273/) (2026)
- [A Model-Driven Lossless Compression Algorithm Resistant to Mismatch](https://mlsanity.com/paper/2601.17684/) (2026)
- [LUMI: Tokenizer-Agnostic LLM-Based Lossless Image Compression](https://mlsanity.com/paper/2607.08221/) (2026)
- [FLM: Frequency-Aware Language Models for Generative Image Compression](https://mlsanity.com/paper/2608.28687/) (2026)
- [HyperZip: Efficient Data Compression through Personalized Diffusion LLMs with Hypernetworks](https://mlsanity.com/paper/2609.36357/) (2026)

## Abstract (arXiv)

We have recently witnessed that ``Intelligence" and `` Compression" are the two sides of the same coin, where the language large model (LLM) with unprecedented intelligence is a general-purpose lossless compressor for various data modalities. This attribute particularly appeals to the lossless image compression community, given the increasing need to compress high-resolution images in the current streaming media era. Consequently, a spontaneous envision emerges: Can the compression performance of the LLM elevate lossless image compression to new heights? However, our findings indicate that the naive application of LLM-based lossless image compressors suffers from a considerable performance gap compared with existing state-of-the-art (SOTA) codecs on common benchmark datasets. In light of this, we are dedicated to fulfilling the unprecedented intelligence (compression) capacity of the LLM for lossless image compression tasks, thereby bridging the gap between theoretical and practical compression performance. Specifically, we propose P2-LLM, a next-pixel prediction-based LLM, which integrates various elaborated insights and methodologies, textite.g., pixel-level priors, the in-context ability of LLM, and a pixel-level semantic preservation strategy, to enhance the understanding capacity of pixel sequences for better next-pixel predictions. Extensive experiments on benchmark datasets demonstrate that P2-LLM can beat SOTA classical and learned codecs.