Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models

Ähnliche Einträge

• MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
  von: Jiang, Chaoya, et al.
  Veröffentlicht: (2024)
• Hallucination Augmented Contrastive Learning for Multimodal Large Language Model
  von: Jiang, Chaoya, et al.
  Veröffentlicht: (2023)
• SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
  von: Jia, Hongrui, et al.
  Veröffentlicht: (2024)
• Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework
  von: Jia, Hongrui, et al.
  Veröffentlicht: (2025)
• TiMix: Text-aware Image Mixing for Effective Vision-Language Pre-training
  von: Jiang, Chaoya, et al.
  Veröffentlicht: (2023)