Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models

Documenti analoghi

• Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning
  di: Qi, Mengshi, et al.
  Pubblicazione: (2025)
• Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization
  di: Qi, Mengshi, et al.
  Pubblicazione: (2025)
• Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation
  di: Qi, Mengshi, et al.
  Pubblicazione: (2025)
• Global-Local Tree Search in VLMs for 3D Indoor Scene Generation
  di: Deng, Wei, et al.
  Pubblicazione: (2025)
• InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
  di: Deng, Nianchen, et al.
  Pubblicazione: (2025)