Technical synopsis
The paper is built around a precise cache-compression story with explicit maths and implementation detail.
A new lossless compression project that combines per-file and per-block codec selection, a compressed model store, and a public demo linked from the GitHub Pages research index.
- Adaptive mixed-precision cache compression
- Recency-aware bit allocation
- Sink-aware reservation for stable anchors
- Head/layer coupling for finer precision control
- Explicit metadata for invertibility and auditing
- Forward-pass wrapping for drop-in use