Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming

Documenti analoghi

• VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
  di: Wang, Yating, et al.
  Pubblicazione: (2025)
• DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models
  di: Zhong, Zhide, et al.
  Pubblicazione: (2026)
• SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
  di: Wang, Hanzhen, et al.
  Pubblicazione: (2025)
• PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model
  di: Liang, Wenqi, et al.
  Pubblicazione: (2025)
• Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy
  di: Zhang, Tianyi, et al.
  Pubblicazione: (2025)