Robust Reasoning via Dynamic Token Selection for Distribution-Aligned Self-Distillation

Documenti analoghi

• From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models
  di: Zhang, Ruiqi, et al.
  Pubblicazione: (2026)
• Less is More: Compact Clue Selection for Efficient Retrieval-Augmented Generation Reasoning
  di: Zhang, Qianchi, et al.
  Pubblicazione: (2025)
• Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation
  di: Chen, Jinwen, et al.
  Pubblicazione: (2025)
• Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
  di: Yan, Shaotian, et al.
  Pubblicazione: (2026)
• Parameter Importance-Driven Continual Learning for Foundation Models
  di: Wang, Lingxiang, et al.
  Pubblicazione: (2025)