AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

Documenti analoghi

• Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation
  di: Gao, Juntao, et al.
  Pubblicazione: (2025)
• VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
  di: Wang, Zixuan, et al.
  Pubblicazione: (2026)
• CoA-VLA: Improving Vision-Language-Action Models via Visual-Textual Chain-of-Affordance
  di: Li, Jinming, et al.
  Pubblicazione: (2024)
• AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  di: Yu, Wenda, et al.
  Pubblicazione: (2026)
• UnderwaterVLA: Dual-brain Vision-Language-Action architecture for Autonomous Underwater Navigation
  di: Wang, Zhangyuan, et al.
  Pubblicazione: (2025)