Claims an RBF-based LLM architecture that reaches global loss optimum in one closed-form iteration without DNN training.
Nonlinearity as rank: Generative low-rank adapter with radial basis functions.Preprint, pages 1–31, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study
Claims an RBF-based LLM architecture that reaches global loss optimum in one closed-form iteration without DNN training.