Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models

Documenti analoghi

• CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
  di: Dang, Yunkai, et al.
  Pubblicazione: (2026)
• UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing
  di: Dang, Yunkai, et al.
  Pubblicazione: (2026)
• FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing
  di: Dang, Yunkai, et al.
  Pubblicazione: (2025)
• TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
  di: Qu, Liao, et al.
  Pubblicazione: (2024)
• Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation
  di: Zhao, Yunpu, et al.
  Pubblicazione: (2025)