JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse

Documenti analoghi

• MCU: An Evaluation Framework for Open-Ended Game Agents
  di: Zheng, Xinyue, et al.
  Pubblicazione: (2023)
• ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting
  di: Cai, Shaofei, et al.
  Pubblicazione: (2024)
• CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
  di: Chen, Peng, et al.
  Pubblicazione: (2025)
• MouseGPT: A Large-scale Vision-Language Model for Mouse Behavior Analysis
  di: Xu, Teng, et al.
  Pubblicazione: (2025)
• VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models
  di: Cheng, Jintao, et al.
  Pubblicazione: (2026)