Do All Individual Layers Help? An Empirical Study of Task-Interfering Layers in Vision-Language Models

Documenti analoghi

• Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching
  di: Wei, Yujie, et al.
  Pubblicazione: (2026)
• UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation
  di: Guo, Jiyu, et al.
  Pubblicazione: (2025)
• Inject Once Survive Later: Backdooring Vision-Language-Action Models to Persist Through Downstream Fine-tuning
  di: Zhou, Jianyi, et al.
  Pubblicazione: (2026)
• LayerMatch: Do Pseudo-labels Benefit All Layers?
  di: Liang, Chaoqi, et al.
  Pubblicazione: (2024)
• Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance
  di: Yang, Wei, et al.
  Pubblicazione: (2026)