Using Composition Operators to Linearize LLM Semantic Transformations
arXiv:2609.22143v1 Announce Type: new Abstract: Machine learning learns functions: prompt to response, image to caption. What these functions are mathematically remains hard to say. We present a method to approximate these kinds of transformations using techniques from dynamical systems that fall u…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-09-22 04:00 · arXiv cs.CL
Using Composition Operators to Linearize LLM Semantic Transformations