Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Sequence-Level Likelihood

Documenti analoghi

• Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
  di: Lin, Xingyu, et al.
  Pubblicazione: (2025)
• Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
  di: Cai, Wang, et al.
  Pubblicazione: (2026)
• Discriminative Policy Optimization for Token-Level Reward Models
  di: Chen, Hongzhan, et al.
  Pubblicazione: (2025)
• GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
  di: Tan, Hongze, et al.
  Pubblicazione: (2025)
• HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark
  di: Wang, Jiacheng, et al.
  Pubblicazione: (2026)