# FLM: Frequency-Aware Language Models for Generative Image Compression

arXiv: https://arxiv.org/abs/2608.28687 · HTML: https://mlsanity.com/paper/2608.28687/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Towards image compression with perfect realism at ultra-low bitrates](https://mlsanity.com/paper/2310.10325/) (2023)
- [Text + Sketch: Image Compression at Ultra Low Rates](https://mlsanity.com/paper/2307.01944/) (2023)
- [Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Prior](https://mlsanity.com/paper/2404.18820/) (2024)
- [WaveDM: Wavelet-Based Diffusion Models for Image Restoration](https://mlsanity.com/paper/2305.13819/) (2023)
- [Lossy Image Compression with Foundation Diffusion Models](https://mlsanity.com/paper/2404.08580/) (2024)
- [StableCodec: Taming One-Step Diffusion for Extreme Image Compression](https://mlsanity.com/paper/2506.21977/) (2025)
- [On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework](https://mlsanity.com/paper/2106.02782/) (2021)
- [OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates](https://mlsanity.com/paper/2505.16091/) (2025)
- [Lossless data compression by large models](https://mlsanity.com/paper/2407.07723/) (2024)
- [Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation](https://mlsanity.com/paper/2406.00758/) (2024)
- [Large Language Model for Lossless Image Compression with Visual Prompts](https://mlsanity.com/paper/2502.16163/) (2025)
- [Optimally Controllable Perceptual Lossy Compression](https://mlsanity.com/paper/2206.10082/) (2022)
- [Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need](https://mlsanity.com/paper/2411.12448/) (2024)
- [The Design, Implementation, and Deployment of a System to Transparently Compress Hundreds of Petabytes of Image Files for a File-Storage Service](https://mlsanity.com/paper/1704.06192/) (2017)
- [Joint Lossless Compression and Steganography for Medical Images via Large Language Models](https://mlsanity.com/paper/2508.01782/) (2025)
- [ByteNet: Rethinking Multimedia File Fragment Classification through Visual Perspectives](https://mlsanity.com/paper/2410.20855/) (2024)
- [Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain](https://mlsanity.com/paper/2203.16357/) (2022)
- [PromptSR: Cascade Prompting for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2507.04118/) (2025)
- [Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior](https://mlsanity.com/paper/2511.22549/) (2025)

## Abstract (arXiv)

Generative models have significantly improved the performance ceiling of image lossy compression at low bitrates by exploiting learned priors. However, the generated textures and semantic details may deviate from the source content, thereby affecting the fidelity of image reconstruction. To solve these challenges, we propose FLM, a frequency-aware language model that improves compression efficiency through frequency-domain probabilistic modeling while retaining deterministic reconstruction. At the encoder, the input image is transformed into quantized DCT coefficients, which are organized into discrete sequences using macroblock-based coefficient tokenization. FLM then performs next-coefficient prediction to autoregressively estimate token-wise conditional probability distributions for arithmetic coding, thereby generating a compact bitstream. At the decoder, the LLM and arithmetic decoder jointly recover the frequency-domain data, followed by inverse transformations for image reconstruction. A task-specific frequency-domain dataset and a two-stage fine-tuning strategy are further developed to enable the model to operate across multiple bitrate settings. FLM is a versatile compressor that is compatible with both lossy compression and lossless JPEG recompression frameworks. Experiments show that FLM exceeds conventional and generative lossy compression methods in rate-distortion performance. FLM achieves BD-PSNR gains of 3.30 dB, 3.83 dB, and 3.80 dB than JPEG baseline on Kodak, Tecnick, and CLIC2020, respectively. Better qualitative quality of FLM can be achieved in improving semantically high fidelity and suppressing blocking artifacts. FLM is also validated to be applicable to the lossless recompression task with competitive performance.