SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment

Documenti analoghi

• Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration
  di: Ji, Wei, et al.
  Pubblicazione: (2024)
• Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
  di: Koo, Jabin, et al.
  Pubblicazione: (2026)
• From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning
  di: Wu, Xinghao, et al.
  Pubblicazione: (2026)
• CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models
  di: Wu, Huiwen, et al.
  Pubblicazione: (2024)
• Gradient Correction in Federated Learning with Adaptive Optimization
  di: Chen, Evan, et al.
  Pubblicazione: (2025)