Sinkhorn Distance Minimization for Knowledge Distillation

Documenti analoghi

• Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models
  di: Cui, Xiao, et al.
  Pubblicazione: (2024)
• Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation
  di: Cui, Xiao, et al.
  Pubblicazione: (2025)
• Exploiting GPT-4 Vision for Zero-shot Point Cloud Understanding
  di: Sun, Qi, et al.
  Pubblicazione: (2024)
• Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling
  di: Cui, Xiao, et al.
  Pubblicazione: (2025)
• Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
  di: Qin, Yulei, et al.
  Pubblicazione: (2025)