Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression

arXiv:2608.11249 · cs.CL, cs.AI, cs.IT, cs.LG, math.IT · Submitted 2026-08-04 · Read on arXiv

Angelo Nardone, Paolo Ferragina

cs.CL, cs.AI, cs.IT, cs.LG, math.IT

Submitted: 2026-08-04

Updated: 2026-08-13

Comments: 18 pages, 11 figures, 2 tables. Main paper: 9 pages (7 pages text + 2 pages references). Includes 9 pages of supplementary material

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 11× in this paper · explained in 2 episodes
• Transformers — 7× in this paper · explained in 2 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Editor — 3× in this paper · explained in 2 episodes
• Hyperparameters — 2× in this paper · explained in 2 episodes
• Quantization — 2× in this paper · explained in 15 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decoder — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 10 episodes
• Diffusion Models — 1× in this paper · explained in 9 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 8 episodes
• Language Models (LLMs) — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 9 episodes
• Operating Regimes — 1× in this paper · explained in 2 episodes
• Papers — 1× in this paper · explained in 3 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 3 episodes
• Performance Gap — 1× in this paper · explained in 2 episodes
• Software Development Kit — 1× in this paper
• Transformer Architecture — 1× in this paper · explained in 4 episodes

Sources

• Asymmetric numeral systems
• DeepZip: Lossless Data Compression using Recurrent Neural Networks
• The Llama 3 Herd of Models
• Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data
• FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression
• AlphaZip: Neural Network-Enhanced Lossless Text Compression
• LLM-based Source Code Compression via Thresholded Symbol Ranking
• LLMZip: Lossless Text Compression using Large Language Models
• Scaling Behavior of Discrete Diffusion Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering