AI RESEARCH
StateSMix: Online Lossless Compression via Mamba State Space Models and Sparse N-gram Context Mixing
arXiv CS.LG
•
ArXi:2605.02904v1 Announce Type: new We present StateSMix, a fully self-contained lossless compressor that couples an online-trained Mamba-style State Space Model (SSM) with sparse n-gram context mixing and arithmetic coding. The model is initialised from scratch and trained token-by-token on the file being compressed, requiring no pre-trained weights, no GPU, and no external dependencies.