Google has published TurboQuant, a KV cache compression algorithm that cuts LLM memory usage by 6x with zero accuracy loss, ...

Serving Large Language Models (LLMs) at scale is a massive engineering challenge because of Key-Value (KV) cache management. As models grow in size and reasoning capability, the KV cache footprint ...

The use of multiple entropy models for Huffman or arithmetic coding is widely used to improve the compression efficiency of many algorithms when the source probability distribution varies. However, ...

ABSTRACT: A new nano-based architectural design of multiple-stream convolutional homeomorphic error-control coding will be conducted, and a corresponding hierarchical implementation of important class ...

SeedBreaker Public Branch v3.2.4 🎉 - Fully working CSPRNG entropy - Multi-API weighted logic - Clean split terminal UI - README with setup and API guide - No private keys exposed" ...

Abstract: Entropy encoding is a term referring to lossless coding technique that replaces data elements with coded representations. Entropy encoding in combination with the transformation and ...

A key question in artificial intelligence is how often models go beyond just regurgitating and remixing what they have learned and produce truly novel ideas or insights. A new project from Google ...

Here are a few smaller projects that demonstrate the compression of texts. Starting with the Huffman Code and the Exponential Golomb Code (exp-golomb).