MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems

Documenti analoghi

• Enhancing Visual Question Answering with Multimodal LLMs via Chain-of-Question Guided Retrieval-Augmented Generation
  di: Xu, Quanxing, et al.
  Pubblicazione: (2026)
• QIRL: Boosting Visual Question Answering via Optimized Question-Image Relation Learning
  di: Xu, Quanxing, et al.
  Pubblicazione: (2025)
• OAD-Promoter: Enhancing Zero-shot VQA using Large Language Models with Object Attribute Description
  di: Xu, Quanxing, et al.
  Pubblicazione: (2025)
• PC-MNet: Dual-Level Congruity Modeling for Multimodal Sarcasm Detection via Polarity-Modulated Attention
  di: Li, Maoheng, et al.
  Pubblicazione: (2026)
• Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning
  di: Zeng, Xingchen, et al.
  Pubblicazione: (2024)