Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought

Documenti analoghi

• Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
  di: Gatmiry, Khashayar, et al.
  Pubblicazione: (2024)
• Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent
  di: Chen, Bo, et al.
  Pubblicazione: (2024)
• Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
  di: Yang, Tong, et al.
  Pubblicazione: (2025)
• Elastic Multi-Gradient Descent for Parallel Continual Learning
  di: Lyu, Fan, et al.
  Pubblicazione: (2024)
• In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
  di: Huang, Sili, et al.
  Pubblicazione: (2024)