VISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action Models

Documenti analoghi

• Schema-Guided Scene-Graph Reasoning based on Multi-Agent Large Language Model System
  di: Chen, Yiye, et al.
  Pubblicazione: (2025)
• Good Weights: Proactive, Adaptive Dead Reckoning Fusion for Continuous and Robust Visual SLAM
  di: Du, Yanwei, et al.
  Pubblicazione: (2025)
• VISTA: Generative Visual Imagination for Vision-and-Language Navigation
  di: Huang, Yanjia, et al.
  Pubblicazione: (2025)
• VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation
  di: Zhang, Chaofan, et al.
  Pubblicazione: (2025)
• CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models
  di: Glossop, Catherine, et al.
  Pubblicazione: (2025)