Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding

Documenti analoghi

• Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems
  di: Tang, Fei, et al.
  Pubblicazione: (2025)
• MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
  di: Shi, Yucheng, et al.
  Pubblicazione: (2025)
• A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models
  di: Wang, Wenkai, et al.
  Pubblicazione: (2025)
• VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
  di: Zhang, Ce, et al.
  Pubblicazione: (2025)
• SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
  di: Cheng, Kanzhi, et al.
  Pubblicazione: (2024)