arXiv (All)
open access
Using Composition Operators to Linearize LLM Semantic Transformations
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 under the umbrella of Koopmanism. We introduce the
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Uncovering the Computational Ingredients of Human-Like Representations in LLMs#819251
- Uncovering the Computational Ingredients of Human-Like Representations in LLMs#809259
- Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs#31319
- Human-Centric Image Captioning with Subject-Centered Spatial Understanding#985668
- VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs#925861
Record · ID 1036826
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive