Position: Good Embodied Reward Models Need Bad Behavior Data

Documenti analoghi

• From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
  di: Wu, Yilin, et al.
  Pubblicazione: (2025)
• Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
  di: Tian, Ran, et al.
  Pubblicazione: (2024)
• Not All Errors Are Made Equal: A Regret Metric for Detecting System-level Trajectory Prediction Failures
  di: Nakamura, Kensuke, et al.
  Pubblicazione: (2024)
• When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering
  di: Yuan, Jessie, et al.
  Pubblicazione: (2026)
• AnySafe: Adapting Latent Safety Filters at Runtime via Safety Constraint Parameterization in the Latent Space
  di: Agrawal, Sankalp, et al.
  Pubblicazione: (2025)