Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation

Documenti analoghi

• uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes
  di: Waheed, Abdul, et al.
  Pubblicazione: (2024)
• Compositional Chain-of-Thought Prompting for Large Multimodal Models
  di: Mitra, Chancharik, et al.
  Pubblicazione: (2023)
• On the Robust Approximation of ASR Metrics
  di: Waheed, Abdul, et al.
  Pubblicazione: (2025)
• Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework
  di: Zhang, Chenyuan, et al.
  Pubblicazione: (2026)
• Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
  di: Mitra, Chancharik, et al.
  Pubblicazione: (2025)