The Invocation Bottleneck in LLM-Based Lossless Compression: What Can Be Removed and What Must Be Traded
cs.IT, cs.DB, math.IT
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/Angie-Yan/LLM-based-DataCompression
Terminology
Sources
- Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding
- Program Synthesis with Large Language Models
- Accelerating Large Language Model Decoding with Speculative Sampling
- Evaluating Large Language Models Trained on Code
- Llamazip: Leveraging LLaMA for Lossless Text Compression and Training Dataset Detection
- Asymmetric numeral systems: entropy coding combining speed of Huffman coding with compression rate of arithmetic coding
- Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction
- Online normalizer calculation for softmax
- FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression
- Qwen2.5 Technical Report
- LLaMA: Open and Efficient Foundation Language Models
- LLMZip: Lossless Text Compression using Large Language Models
Related papers
- The Gaussian Multiuser Channel Capacity Region
- The mathematical landscape of partial information decomposition: A comprehensive review of properties and measures
- Electromagnetic Signal and Information Theory: A Continuous-Aperture Array Perspective
- Analytically Characterized Optimal Power Control for Signal-Level-Integrated Sensing, Computing and Communication in Federated Learning
- Information Spectrum Methods for Multiple-Access Channels--Part I: epsilon-Capacity Regions in the Mixed Gaussian Case
- Seed Recycling: Explicit Codes for Mixed Synchronization Errors Matching the Leading Term of the Gilbert--Varshamov Bound