AME: Aligned Manifold Entropy for Robust Vision-Language Distillation

Documenti analoghi

• Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning
  di: Chen, Dexia, et al.
  Pubblicazione: (2025)
• Entropy Reveals Block Importance in Masked Self-Supervised Vision Transformers
  di: Xiang, Peihao, et al.
  Pubblicazione: (2026)
• The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models
  di: Chopra, Shivang, et al.
  Pubblicazione: (2026)
• A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
  di: Jing, Liqiang, et al.
  Pubblicazione: (2025)
• Rotation Perturbation Robustness in Point Cloud Analysis: A Perspective of Manifold Distillation
  di: Xu, Xinyu, et al.
  Pubblicazione: (2024)