ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $α$-$β$-Divergence

Documenti analoghi

• The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works
  di: Wang, Guanghui, et al.
  Pubblicazione: (2026)
• OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning
  di: Hua, Cong, et al.
  Pubblicazione: (2025)
• Optimizing Partial Area Under the Top-k Curve: Theory and Practice
  di: Wang, Zitai, et al.
  Pubblicazione: (2022)
• Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
  di: Li, Sicong, et al.
  Pubblicazione: (2025)
• A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization
  di: Wang, Zitai, et al.
  Pubblicazione: (2023)