Castuner

RoboPapers

Chris Paxton and Michael Cho

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

Sito del podcast

Ascoltalo nella tua app

Episodi

114 episodi

  1. Ep#115: Delta-0 (Δ₀): A New Chapter in Humanoid Intelligence 1:09:46
  2. Ep#114: Oopsie Data 44:22
  3. Ep#113: MolmoBOT: Large-Scale Simulation Enables Zero-Shot Manipulation 39:16
  4. Ep#112: SlipSense and Touch2Trace 1:02:10
  5. Ep#111: SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning 53:03
  6. Ep#110: ENPIRE: Agentic Robot PolicySelf-Improvement in the Real World 53:36
  7. Ep#109: Enigma - Connecting 100 Robots To The Internet 48:57
  8. Ep#108: VLS: Steering Pretrained Robot Policies via Vision–Language Models 51:56
  9. Ep#107: Do As I Do: Dexterous Manipulation Data from Everyday Human Videos 1:02:32
  10. Ep#106: Flex-π: A Multi-Stream World-Action Model with Compute Flexibility 53:31
  11. Ep#105: Beyond Imitation: Self-Improving Robot Policies via Off-Policy Q-Planning 49:35
  12. Ep#104: Light-Loco-Parkour: Versatile Perceptive Whole-Body Locomotion via Multi-Skill Distillation 42:45
  13. Ep#103: Freeform Preference Learning for Robotic Manipulation 47:58
  14. Ep#102: EgoSuite-Open100K from Lightwheel 1:09:09
  15. Ep#101: Coupled Local and Global World Models for Efficient First Order RL 51:26
  16. Ep#100: 100 Episodes of Embodied AI 1:29:00
  17. Ep#99: DYNA-2: A 1 Million Hour Scaling Law for World-Action Models 1:07:19
  18. Ep#97: Cross-Embodiment Robot Manipulation via a Unified Hand Action Space 59:53
  19. Ep#96: EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration 36:32
  20. Ep#95: Action-to-Action Flow Matching 49:19
  21. Ep#94: Learning a Thousand Tasks in a Day 1:16:39
  22. Ep#93: CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy 1:00:09
  23. Ep#92: Human Universal Grasping 1:10:03
  24. Ep#91: RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies 56:38
  25. Ep#90: From Capable Controllers to Deployable Humanoid Systems 1:02:32
  26. Ep#89: Contact Grounded Policy 39:20
  27. Ep#88: DexSkin: High-Coverage Conformable Robotic Skin for Learning Contact-Rich Manipulation 55:05
  28. Ep#87: MolmoAct 2: An open foundation for robots that work in the real world 1:02:24
  29. Ep#86: RISE: Self-Improving Robot Policy with Compositional World Model 53:46
  30. Ep#85: Tutor Intelligence 1:01:04
  31. Ep#84: Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons 59:14
  32. Ep#83: PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation 1:22:44
  33. Ep#82: SimTooReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation 54:37
  34. Ep#81: mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs 1:08:44
  35. Ep#80: LATENT: Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data 55:31
  36. Ep#79: Rhoda AI - Causal Video Models Are Data-Efficient Robot Policy Learners 1:09:11
  37. Ep#78: Three Eras of Robot Learning 1:10:46
  38. Ep#77: DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos 1:02:59
  39. Ep#76: OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control 48:22
  40. Ep#75: TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics 1:01:20
  41. Ep#74: Weave Robotics 46:59
  42. Ep#73: VideoManip: Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction 44:21
  43. Ep#72: SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control 59:44
  44. Ep#71: Build Your Own Robot 1:01:11
  45. Ep#70: A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation 1:24:53
  46. Ep#69: MolmoSpaces, an Open Ecosystem for Embodied AI 1:11:00
  47. Ep#68: DreamZero: World Action Models are Zero-Shot Policies 42:31
  48. Ep#67: Asimov - Open Source Humanoid 52:46
  49. Ep#66: Ordered Action Tokenization 51:43
  50. Ep#65: VLM4VLA: Revisiting Vision-Language Models in Vision-Language-Action Models 1:03:46