SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization

Documenti analoghi

• MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
  di: Jiang, Chaoya, et al.
  Pubblicazione: (2024)
• Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework
  di: Jia, Hongrui, et al.
  Pubblicazione: (2025)
• Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models
  di: Jiang, Chaoya, et al.
  Pubblicazione: (2024)
• Hallucination Augmented Contrastive Learning for Multimodal Large Language Model
  di: Jiang, Chaoya, et al.
  Pubblicazione: (2023)
• From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models
  di: Jia, Hongrui, et al.
  Pubblicazione: (2026)