CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games

Documenti analoghi

• Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case
  di: Chen, Peng, et al.
  Pubblicazione: (2024)
• Moral Combat: Disagreement in Action, Not Belief
  di: Michael S. Moore
  Pubblicazione: (2020)
• FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
  di: Wang, Xin, et al.
  Pubblicazione: (2025)
• Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training
  di: Gu, Jihao, et al.
  Pubblicazione: (2025)
• CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
  di: Du, Fan, et al.
  Pubblicazione: (2026)