A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers

Documenti analoghi

• The Expressive Power of Transformers with Chain of Thought
  di: Merrill, William, et al.
  Pubblicazione: (2023)
• Exact Expressive Power of Transformers with Padding
  di: Merrill, William, et al.
  Pubblicazione: (2025)
• A Logic for Expressing Log-Precision Transformers
  di: Merrill, William, et al.
  Pubblicazione: (2022)
• Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
  di: Svete, Anej, et al.
  Pubblicazione: (2026)
• The Illusion of State in State-Space Models
  di: Merrill, William, et al.
  Pubblicazione: (2024)