Michael S. Ryoo

収録論文 18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

• LACE: Latent Visual Representation for Cross-Embodiment Learning
  2026/5/1
• Robotic VLA Benefits from Joint Learning with Motion Image Diffusion
  2025/12/1
• Pixel Motion Diffusion is What We Need for Robot Control
  2025/9/1
• LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
  2024/6/28
• LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
  2024/6/1
• Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning
  2023/7/1
• Active Vision Reinforcement Learning under Limited Visual Observability
  2023/6/1
• Energy-Based Models for Cross-Modal Localization using Convolutional Transformers
  2023/6/1
• Token Turing Machines
  2022/11/1
• Open-vocabulary Queryable Scene Representations for Real World Planning
  2022/9/1
• Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
  2022/6/1
• Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
  2022/6/1
• Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning
  2021/8/1
• Visionary: Vision architecture discovery for robot learning
  2021/3/1
• Model-based Behavioral Cloning with Future Image Similarity Learning
  2019/10/1
• Learning Real-World Robot Policies by Dreaming
  2018/5/1
• Learning Robot Activities from First-Person Human Videos Using Convolutional Future Regression
  2017/3/1
• Learning Social Affordance Grammar from Videos: Transferring Human Interactions to Human-Robot Interactions
  2017/3/1