Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models

Documenti analoghi

• MMSD3.0: A Multi-Image Benchmark for Real-World Multimodal Sarcasm Detection
  di: Zhao, Haochen, et al.
  Pubblicazione: (2025)
• SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models
  di: Ying, Zonghao, et al.
  Pubblicazione: (2024)
• REMOTE: A Unified Multimodal Relation Extraction Framework with Multilevel Optimal Transport and Mixture-of-Experts
  di: Lin, Xinkui, et al.
  Pubblicazione: (2025)
• UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
  di: Wen, Zimo, et al.
  Pubblicazione: (2026)
• MMIDR: Teaching Large Language Model to Interpret Multimodal Misinformation via Knowledge Distillation
  di: Wang, Longzheng, et al.
  Pubblicazione: (2024)