OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection

Documenti analoghi

• Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning
  di: Liu, Jiaqi, et al.
  Pubblicazione: (2025)
• Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling
  di: Yu, Xinlei, et al.
  Pubblicazione: (2025)
• ViFP: A Framework for Visual False Positive Detection to Enhance Reasoning Reliability in VLMs
  di: Zhang, Ben, et al.
  Pubblicazione: (2025)
• VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework
  di: Wang, Chao, et al.
  Pubblicazione: (2025)
• Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
  di: Liu, Junming, et al.
  Pubblicazione: (2026)