Clustering Head: A Visual Case Study of the Training Dynamics in Transformers

Documenti analoghi

• Easing Optimization Paths: a Circuit Perspective
  di: Odonnat, Ambroise, et al.
  Pubblicazione: (2025)
• Provable Benefits of In-Tool Learning for Large Language Models
  di: Houliston, Sam, et al.
  Pubblicazione: (2025)
• Iteration Head: A Mechanistic Study of Chain-of-Thought
  di: Cabannes, Vivien, et al.
  Pubblicazione: (2024)
• Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
  di: Odonnat, Ambroise, et al.
  Pubblicazione: (2023)
• Optimal Self-Consistency for Efficient Reasoning with Large Language Models
  di: Feng, Austin, et al.
  Pubblicazione: (2025)