Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory

Documenti analoghi

• Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
  di: Ettori, Davide
  Pubblicazione: (2026)
• Exploring Graph Structure Comprehension Ability of Multimodal Large Language Models: Case Studies
  di: Zhong, Zhiqiang, et al.
  Pubblicazione: (2024)
• Beyond Frequency: The Role of Redundancy in Large Language Model Memorization
  di: Zhang, Jie, et al.
  Pubblicazione: (2025)
• Model-Distributed Inference for Large Language Models at the Edge
  di: Macario, Davide, et al.
  Pubblicazione: (2025)
• Quantifying the Reconstructability of Astrophysical Methods with Large Language Models and Information Theory: A Case Study in Spectral Reconstruction
  di: Lin, Hsing Wen, et al.
  Pubblicazione: (2026)