Diversity-Aware Reverse Kullback-Leibler Divergence for Large Language Model Distillation

Documenti analoghi

• Rethinking the Role of Temperature in Large Language Model Distillation
  di: Luong, Hoang-Chau, et al.
  Pubblicazione: (2026)
• Better Estimation of the Kullback--Leibler Divergence Between Language Models
  di: Amini, Afra, et al.
  Pubblicazione: (2025)
• Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation
  di: Lv, Jiaming, et al.
  Pubblicazione: (2024)
• Consistently Informative Soft-Label Temperature for Knowledge Distillation
  di: Luong, Hoang-Chau, et al.
  Pubblicazione: (2026)
• Generalized Kullback-Leibler Divergence Loss
  di: Cui, Jiequan, et al.
  Pubblicazione: (2025)