DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training

Documenti analoghi

• DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
  di: Zhu, Dingwei, et al.
  Pubblicazione: (2026)
• VRPO: Rethinking Value Modeling for Robust RL Training under Noisy Supervision
  di: Zhu, Dingwei, et al.
  Pubblicazione: (2025)
• JFTA-Bench: Evaluate LLM's Ability of Tracking and Analyzing Malfunctions Using Fault Trees
  di: Wang, Yuhui, et al.
  Pubblicazione: (2026)
• EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training
  di: Pan, Chengjun, et al.
  Pubblicazione: (2026)
• CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
  di: Lv, Huijie, et al.
  Pubblicazione: (2024)