Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimization

Documenti analoghi

• MVP: Multiple View Prediction Improves GUI Grounding
  di: Zhang, Yunzhu, et al.
  Pubblicazione: (2025)
• Mitigating Conversational Inertia in Multi-Turn Agents
  di: Wan, Yang, et al.
  Pubblicazione: (2026)
• Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
  di: Zhao, Shuai, et al.
  Pubblicazione: (2023)
• DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization
  di: Zhang, Chao, et al.
  Pubblicazione: (2025)
• Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data
  di: Zhao, Shuai, et al.
  Pubblicazione: (2025)