AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training

Documenti analoghi

• Token-Level Uncertainty-Aware Objective for Language Model Post-Training
  di: Liu, Tingkai, et al.
  Pubblicazione: (2025)
• Training Text-to-Molecule Models with Context-Aware Tokenization
  di: Kim, Seojin, et al.
  Pubblicazione: (2025)
• Training-Trajectory-Aware Token Selection
  di: Shen, Zhanming, et al.
  Pubblicazione: (2026)
• TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation
  di: Qu, Haohao, et al.
  Pubblicazione: (2024)
• SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling
  di: Liu, Dong, et al.
  Pubblicazione: (2025)