Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing

Documenti analoghi

• Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation
  di: Rang, Miao, et al.
  Pubblicazione: (2025)
• An Empirical Study of Scaling Law for OCR
  di: Rang, Miao, et al.
  Pubblicazione: (2023)
• Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
  di: Bi, Zhenni, et al.
  Pubblicazione: (2024)
• Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts
  di: Rang, Miao, et al.
  Pubblicazione: (2025)
• VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse
  di: Nie, Ying, et al.
  Pubblicazione: (2025)