Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain

Documenti analoghi

• Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
  di: Kim, Jihyo, et al.
  Pubblicazione: (2024)
• StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention
  di: Seo, Seungwon, et al.
  Pubblicazione: (2024)
• Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection
  di: Lee, Uichan, et al.
  Pubblicazione: (2026)
• Concept-skill Transferability-based Data Selection for Large Vision-Language Models
  di: Lee, Jaewoo, et al.
  Pubblicazione: (2024)
• Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations
  di: Kim, Jeonghyeon, et al.
  Pubblicazione: (2025)