Transforms for LLM Quantization: The Great Inversion and Format Co-Design
Most competitive 4-bit LLM research pipelines now open the same way: apply a linear, function-preserving transform (rotation, scaling, permutation, non-orthogonal affine) so the outlier mass sits more favorably against the group scales, and only then round. Yet we are aware of no survey dedicated to this transform stage, and its literature is quietly re-deriving an older theory. We identify and formalize the principle that organizes it, the Great Inversion: allocation-flexible coding rewards energy concentration, whereas the grouped shared-scale quantization a deployed matrix instruction performs rewards within-group flattening. Classical transform coding (1963: decorrelate, allocate bits...
| Authors | Ehsan Jokar |
|---|---|
| Primary category | cs.LG |
| Published | 25 August 2026 |
| Last updated at source | 25 August 2026 |
Connected in the knowledge graph
- ewin-reg/WeMM-Embedding-2B-GGUFModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.