AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations

Documenti analoghi

• GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation Learning
  di: Banayeeanzade, Amin, et al.
  Pubblicazione: (2025)
• ViSaRL: Visual Reinforcement Learning Guided by Human Saliency
  di: Liang, Anthony, et al.
  Pubblicazione: (2024)
• CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations
  di: Liang, Anthony, et al.
  Pubblicazione: (2025)
• Batch Active Learning of Reward Functions from Human Preferences
  di: Bıyık, Erdem, et al.
  Pubblicazione: (2024)
• MILE: Model-based Intervention Learning
  di: Korkmaz, Yigit, et al.
  Pubblicazione: (2025)