Abstract: As an alternative implementation of Slepian-Wolf coding, distributed arithmetic coding is very competitive in short and medium block lengths. The existing distributed arithmetic coding ...

Abstract: Convolutional neural networks (CNNs) have gained a huge attention for real‐world artificial intelligence (AI) applications such as image classification and object detection. On the other ...

A Python library for steganographic encoding and decoding using arithmetic coding to hide secret messages within LLM-generated text. The key insight is that by carefully selecting which tokens to ...

[Note this is an in-progress specification to be used in an upcoming format.] The decoder supports adaptive binary and multi-symbol models, as well as specialized encoding schemes like truncated ...

“LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of ...