RoboPapers

Autor: Chris Paxton and Michael Cho

Chris Paxton & Michael Cho geek out over robotic papers with paper authors. robopapers.substack.com

Odcinki

1. Ep#112: SlipSense and Touch2Trace – RoboPapers
2. Ep#111: SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning – RoboPapers
3. Ep#110: ENPIRE: Agentic Robot PolicySelf-Improvement in the Real World – RoboPapers
4. Ep#109: Enigma - Connecting 100 Robots To The Internet – RoboPapers
5. Ep#108: VLS: Steering Pretrained Robot Policies via Vision–Language Models – RoboPapers
6. Ep#107: Do As I Do: Dexterous Manipulation Data from Everyday Human Videos – RoboPapers
7. Ep#106: Flex-π: A Multi-Stream World-Action Model with Compute Flexibility – RoboPapers
8. Ep#105: Beyond Imitation: Self-Improving Robot Policies via Off-Policy Q-Planning – RoboPapers
9. Ep#104: Light-Loco-Parkour: Versatile Perceptive Whole-Body Locomotion via Multi-Skill Distillation – RoboPapers
10. Ep#103: Freeform Preference Learning for Robotic Manipulation – RoboPapers
11. Ep#102: EgoSuite-Open100K from Lightwheel – RoboPapers
12. Ep#101: Coupled Local and Global World Models for Efficient First Order RL – RoboPapers
13. Ep#100: 100 Episodes of Embodied AI – RoboPapers
14. Ep#99: DYNA-2: A 1 Million Hour Scaling Law for World-Action Models – RoboPapers
15. Ep#97: Cross-Embodiment Robot Manipulation via a Unified Hand Action Space – RoboPapers
16. Ep#96: EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration – RoboPapers
17. Ep#95: Action-to-Action Flow Matching – RoboPapers
18. Ep#94: Learning a Thousand Tasks in a Day – RoboPapers
19. Ep#93: CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy – RoboPapers
20. Ep#92: Human Universal Grasping – RoboPapers
21. Ep#91: RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies – RoboPapers
22. Ep#90: From Capable Controllers to Deployable Humanoid Systems – RoboPapers
23. Ep#89: Contact Grounded Policy – RoboPapers
24. Ep#88: DexSkin: High-Coverage Conformable Robotic Skin for Learning Contact-Rich Manipulation – RoboPapers
25. Ep#87: MolmoAct 2: An open foundation for robots that work in the real world – RoboPapers
26. Ep#86: RISE: Self-Improving Robot Policy with Compositional World Model – RoboPapers
27. Ep#85: Tutor Intelligence – RoboPapers
28. Ep#84: Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons – RoboPapers
29. Ep#83: PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation – RoboPapers
30. Ep#82: SimTooReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation – RoboPapers