Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models

Documenti analoghi

• Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?
  di: Liao, Yuan-Hong, et al.
  Pubblicazione: (2024)
• LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception
  di: Liao, Yuan-Hong, et al.
  Pubblicazione: (2025)
• Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning
  di: Tang, Yihong, et al.
  Pubblicazione: (2024)
• Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions
  di: Acuna, David, et al.
  Pubblicazione: (2025)
• Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models
  di: Stogiannidis, Ilias, et al.
  Pubblicazione: (2025)