Conference on Robot Learning (CoRL)
Writing down some of the papers that seem interesting to me that I should take a read at.
- Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning
- Legged Locomotion in Challenging Terrains using Egocentric Vision
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools
- Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
- Distilled Feature Fields Enable Few-Shot Manipulation
- MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
- Robot Parkour Learning
- Predicting Object Interactions with Behavior Primitives: An Application in Stowing Tasks
- Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping
2025
- Visual Imitation Enables Contextual Humanoid Control
- Steering Your Diffusion Policy with Latent Space Reinforcement Learning
- LocoFormer: Generalist Locomotion via Long-Context Adaptation
- Contribution is cross-embodiment training for WBC, and long horizon
Interesting Workshops:
- https://leap-workshop.github.io/ (cool for long-horizon planning)
- https://robot-world-modeling.github.io/ (world models buzzword)
- https://sites.google.com/view/h2r-corl2025/home (using human-centric data for training robots
- https://sites.google.com/stanford.edu/corldata25/home (mostly about data)
- https://rational-robots.github.io/ (scaling laws?)