Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation

Documenti analoghi

• Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment
  di: Park, Hyuntae, et al.
  Pubblicazione: (2025)
• Grokfast: Accelerated Grokking by Amplifying Slow Gradients
  di: Lee, Jaerin, et al.
  Pubblicazione: (2024)
• CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning
  di: Kim, Yeachan, et al.
  Pubblicazione: (2024)
• Censored Sampling for Topology Design: Guiding Diffusion with Human Preferences
  di: Kim, Euihyun, et al.
  Pubblicazione: (2025)
• Expressive Power of ReLU and Step Networks under Floating-Point Operations
  di: Park, Yeachan, et al.
  Pubblicazione: (2024)