PKG-DPO: Optimizing Domain-Specific AI systems with Physics Knowledge Graphs and Direct Preference Optimization

Documenti analoghi

• TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
  di: Abdullah, Abdulhady Abas, et al.
  Pubblicazione: (2026)
• $β$-DPO: Direct Preference Optimization with Dynamic $β$
  di: Wu, Junkang, et al.
  Pubblicazione: (2024)
• C2-DPO: Constrained Controlled Direct Preference Optimization
  di: Asadi, Kavosh, et al.
  Pubblicazione: (2025)
• Mix- and MoE-DPO: A Variational Inference Approach to Direct Preference Optimization
  di: Bohne, Jason, et al.
  Pubblicazione: (2025)
• AnnoDPO: Protein Functional Annotation Learning with Direct Preference Optimization
  di: Jiang, Zixuan, et al.
  Pubblicazione: (2025)