Scholar
Younggyo Seo
Google Scholar ID: tI1-YwIAAAAJ
Amazon FAR (Frontier AI & Robotics)
Citations & Impact
Citations
1,697
H-index
17
i10-index
20
Publications
20
Co-authors
39
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- 1. FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control
- 2. HAMLET: Switch Your Vision-Language-Action Model into a History-Aware Policy
- 3. ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context
- 4. DEAS: Detached Value Learning with Action Sequence for Scalable Offline RL
- 5. Contrastive Representation Regularization for Vision-Language-Action Models
- 6. Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
- 7. Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Robot Learning
Research Experience
- Currently a researcher at Amazon Frontier AI & Robotics (FAR) team, working with Pieter Abbeel. Previously, he was a postdoctoral scholar at UC Berkeley, working with Pieter Abbeel, and a research scientist at Dyson Robot Learning Lab, working with Stephen James, focusing on training robots with reinforcement learning.
Education
- Ph.D. from KAIST, advised by Jinwoo Shin; during the Ph.D., he was a visiting scholar at UC Berkeley working with Pieter Abbeel and Kimin Lee, and interned at Microsoft Research Asia.
Background
- Research Interests: reinforcement learning, world models, video generation, and representation learning. Professional Field: developing intelligent robots that achieve super-human performance.
Miscellany
- Contact: mail AT younggyo.me
- Other Platforms: Google Scholar / Twitter / Github
