Feature Resemblance: Towards a Theoretical Understanding of Analogical Reasoning in Transformers

Documenti analoghi

• Provable Knowledge Acquisition and Extraction in One-Layer Transformers
  di: Xu, Ruichen, et al.
  Pubblicazione: (2025)
• Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
  di: Hellwig, Philipp, et al.
  Pubblicazione: (2026)
• Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data
  di: Xing, Yue, et al.
  Pubblicazione: (2024)
• Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
  di: Zhu, Hanlin, et al.
  Pubblicazione: (2024)
• Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective
  di: Shao, Jintian, et al.
  Pubblicazione: (2025)