More than A Point: Capturing Uncertainty with Adaptive Affordance Heatmaps for Spatial Grounding in Robotic Tasks

Documenti analoghi

• OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning
  di: Liu, Yuecheng, et al.
  Pubblicazione: (2025)
• EVLP:Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning
  di: Cai, Xinyan, et al.
  Pubblicazione: (2025)
• SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning
  di: Liu, Yuecheng, et al.
  Pubblicazione: (2025)
• AffordanceSAM: Segment Anything Once More in Affordance Grounding
  di: Jiang, Dengyang, et al.
  Pubblicazione: (2025)
• ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models
  di: Zhang, Lingfeng, et al.
  Pubblicazione: (2024)