PAQ8PX – Experimental Lossless Data Compressor & Entropy Estimator

AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.

Offline Dictionary-based Compression (Re-Pair, Recursive Pairing)

Code and data for VTCBench, a VLM benchmark for long-context understanding capabilities under vision-text compression paradigm.

LLMA = LLM + Arithmetic coder, which use LLM to do insane text data compression. LLMA=大模型+算术编码，它能使用LLM对文本数据进行暴力的压缩，达到极高的压缩率。

No description provided.

Extreme inline text compression for HTML / JS. A custom pipeline that generates stand-alone HTML or JS files which embed competitively compressed self-extracting text, with file sizes of 25% - 40% the original.

本项目是基于 Java 实现的哈夫曼编码文本压缩解压工具，按照字符频率构建哈夫曼树、生成哈夫曼编码映射、压缩解压文件。 This project is a Huffman coding-based text compression and decompression tool implemented in Java. It constructs a Huffman tree according to character frequencies, generates Huffman coding mappings, and enables file compression and decompression.

🍶 llm-distillery ⇢ use LLMs to run map-reduce summarization tasks on large documents until a target token size is met.

This project is about the implementation of the LZ77 and Deflate COMPRESSION algorithm.

A simple visualization for huffman tree, which is used in encoding text.

Text compression tool ⚡

Cross platform diff engine for .net core used to compare string values and generate a comparison output

Using Huffman code to encode and compress the secret text data along with using histogram shifting to encode the data into the image.

Easy data compression algorithm.

Huffman code

LZ77 algorithm, providing efficient lossless data compression and decompression capabilities. It offers a reliable and flexible solution for reducing file sizes in various programming languages.

An attempt to compress the enwik8 file

A text compression tool & library

Data driven approach for compressing text using an encoder-decoder architecture and word-level embeddings.

No description provided.

A simple python implementation for the well-known compression algorithm LZW

A Java program that implements (4) four lossless text compression techniques for ASCII Text and compares compression ratio.

Compressor for UTF-8 encoded text

Official Implementation of Paper "A Novel Metric for Evaluating Semantics Preservation"

End-to-End Python implementation of CompactPrompt (Choi et al., 2025): a unified pipeline for LLM prompt and data compression. Features modular compression pipeline with dependency-driven phrase pruning, reversible n-gram encoding, K-means quantization, and embedding-based exemplar selection. Achieves 2-4x token reduction while preserving accuracy.

The DCW stands for Damn Compression Wizard and is basically what it sounds like, a compression app that can compress a text file using Huffman Code (Lossless))

Highlights the key matches between your Given PDF and the description text

Text compression by abbreviation

기존 카카오 문자열 문제에서 더 세밀하게 압축하는 알고리즘 테스트