DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training

Documenti analoghi

• DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning
  di: Cao, Qi, et al.
  Pubblicazione: (2025)
• DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding
  di: Zhang, Ruiyi, et al.
  Pubblicazione: (2025)
• FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation
  di: Zhang, Ruiyi, et al.
  Pubblicazione: (2026)
• VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
  di: Zeng, Thomas, et al.
  Pubblicazione: (2025)
• EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing
  di: Shihab, Ibne Farabi, et al.
  Pubblicazione: (2026)