An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivity

Documenti analoghi

• Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation
  di: Chen, Beitao, et al.
  Pubblicazione: (2025)
• Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval
  di: Li, Hao, et al.
  Pubblicazione: (2023)
• SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
  di: Chen, Beitao, et al.
  Pubblicazione: (2025)
• VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization
  di: Zhou, Yixuan, et al.
  Pubblicazione: (2024)
• DePT: Decoupled Prompt Tuning
  di: Zhang, Ji, et al.
  Pubblicazione: (2023)