Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization

Documenti analoghi

• Data Mixing Can Induce Phase Transitions in Knowledge Acquisition
  di: Gu, Xinran, et al.
  Pubblicazione: (2025)
• Research and Implementation of Data Enhancement Techniques for Graph Neural Networks
  di: Gu, Jingzhao, et al.
  Pubblicazione: (2024)
• A Quadratic Synchronization Rule for Distributed Deep Learning
  di: Gu, Xinran, et al.
  Pubblicazione: (2023)
• Understanding Nonlinear Implicit Bias via Region Counts in Input Space
  di: Li, Jingwei, et al.
  Pubblicazione: (2025)
• Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning
  di: Liu, Siyuan, et al.
  Pubblicazione: (2026)