Yigit Korkmaz

収録論文 6本 ・ フィジカルAI/ロボット学習

※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。

論文

• Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
  2026/3/1
• Causally Robust Reward Learning from Reason-Augmented Preference Feedback
  2026/3/1
• When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
  2025/10/1
• Actor-Free Continuous Control via Structurally Maximizable Q-Functions
  2025/10/1
• MILE: Model-based Intervention Learning
  2025/2/1
• CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
  2024/2/1