Scholar
Toru Lin
Google Scholar ID: Rxb7o6IAAAAJ
UC Berkeley
Citations & Impact
Citations
417
H-index
8
i10-index
7
Publications
9
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Published multiple papers including 'Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning' (arXiv 2025) and 'Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids' (CoRL 2025).
Research Experience
- Interned at NVIDIA GEAR group (2024), DeepMind (2021, 2019), Facebook (2018), and Google (2017, 2016); Teaching/Lab assistant for courses like UC Berkeley CS 294-277 Robots That Learn (Fall 2024), MIT 6.819/6.869 Advances in Computer Vision (Spring 2021), etc.
Education
- PhD: University of California, Berkeley (BAIR), Advisor: Jitendra Malik; BSc and MEng: Massachusetts Institute of Technology EECS, Advisors: Phillip Isola and Antonio Torralba; Undergraduate studies at The University of Tokyo initially.
Background
- Research Interests: Developing real-world robotic systems capable of generalizable dexterous manipulation and robust whole-body control through end-to-end learning, leveraging data from both the real world and simulation. Expertise: reinforcement learning, imitation learning, sim-to-real, generative models. Mentors include Jitendra Malik and Alexei Efros.
Miscellany
- Speaks English, Japanese, Mandarin, Cantonese, and Singlish. Enjoys reading philosophy, learning physics, and making art outside of research.
Co-authors