pith. sign in

Locating and editing factual associations in gpt

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 1 cs.LG 1

years

2025 1 2024 1

roles

background 1

polarities

background 1

representative citing papers

KAN: Kolmogorov-Arnold Networks

cs.LG · 2024-04-30 · conditional · novelty 8.0

KANs with learnable univariate spline activations on edges achieve better accuracy than MLPs with fewer parameters, faster scaling, and direct visualization for scientific discovery.

citing papers explorer

Showing 2 of 2 citing papers.

  • KAN: Kolmogorov-Arnold Networks cs.LG · 2024-04-30 · conditional · none · ref 81

    KANs with learnable univariate spline activations on edges achieve better accuracy than MLPs with fewer parameters, faster scaling, and direct visualization for scientific discovery.

  • FoNE: Precise Single-Token Number Embeddings via Fourier Features cs.CL · 2025-02-13 · unverdicted · none · ref 27

    FoNE encodes numbers as single tokens via Fourier features and outperforms subword and digit-wise embeddings on addition, subtraction, and multiplication with far less data.