MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents

Documenti analoghi

• Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation
  di: Wei, Ziming, et al.
  Pubblicazione: (2025)
• Structured Preference Optimization for Vision-Language Long-Horizon Task Planning
  di: Liang, Xiwen, et al.
  Pubblicazione: (2025)
• Correctable Landmark Discovery via Large Models for Vision-Language Navigation
  di: Lin, Bingqian, et al.
  Pubblicazione: (2024)
• NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning
  di: Lin, Bingqian, et al.
  Pubblicazione: (2024)
• EchoVLA: Synergistic Declarative Memory for VLA-Driven Mobile Manipulation
  di: Lin, Min, et al.
  Pubblicazione: (2025)