Yen-Jen Wang 王彥仁

Building physical AGI. From algorithms to atoms.

I am a Ph.D. student at UC Berkeley, advised by Professors Pieter Abbeel and Shankar Sastry, working closely with Professor Haozhi Qi, and interning at Amazon FAR. Early in my Ph.D., I worked closely with Professors Koushil Sreenath and Jitendra Malik.

I build learning systems that connect vision-language reasoning, whole-body control, and dexterous manipulation — toward general-purpose humanoids that operate in the real world.

Before Berkeley, I was Robot Era's founding roboticist, where I led the humanoid algorithm team and built the stack from the ground up. Later I contributed to its video world model and dexterous hand. I received my M.S. from Tsinghua IIIS (Outstanding Graduate, advised by Professor Jianyu Chen) and B.S. from National Taiwan University. Before robotics, I represented Taiwan at the International Olympiad in Informatics and the ICPC World Finals (5th place).

Selected Awards

2024

Best Paper Award Finalist Robotics: Science and Systems (RSS)

Official Website
2019

5th Place (Silver Medal), International Collegiate Programming Contest (ICPC) World Finals

ICPC Profile Codebook & Practice Records
2017

Silver Medal, International Olympiad in Informatics (IOI)

IOI Profile

Selected Papers

A curated selection. For all papers, see Publications or my Google Scholar.

VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes

Yen-Jen Wang^*, Jiaman Li^*,‡, Sirui Chen^§, Takara E. Truong^§, Pei Xu^§, Pieter Abbeel^†, Rocky Duan^†, Koushil Sreenath^†, Angjoo Kanazawa^†, Carmelo Sferrazza^†, Guanya Shi^†, C. Karen Liu^†

* Co-first authors · ‡ Project lead · § Equal contribution · † Amazon FAR Team Co-Lead

Tech Report, June 2026

Paper Project Page Video
Learning Dexterous Manipulation Skills from Imperfect Simulations

Elvis Hsieh^*, Wen-Han Hsieh^*, Yen-Jen Wang^*, Toru Lin, Jitendra Malik, Koushil Sreenath^†, Haozhi Qi^†

* Equal contribution (listed in alphabetical order). · † Equal advising.

IEEE International Conference on Robotics & Automation (ICRA), 2026

Paper Code Project Page
MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning

Yuanchen Ju^*, Yongyuan Liang^*, Yen-Jen Wang^*, Nandiraju Gireesh, Yuanliang Ju, Seungjae Lee, Qiao Gu, Elvis Hsieh, Furong Huang^†, Koushil Sreenath^†

∗ Equal Contribution · † Equal Advising

International Conference on Learning Representations (ICLR), 2026 Oral (Top 1%)

Paper Code Project Page
Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning

Xinyang Gu^*, Yen-Jen Wang^*, Xiang Zhu^*, Chengming Shi^*, Yanjiang Guo, Yichen Liu, Jianyu Chen^†

∗ Equal contribution. Project Co-lead. · † Corresponding Author.

Robotics: Science and Systems (RSS), 2024 Best Paper Award Finalist

Paper Code Project Page Video
Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer

Xinyang Gu^*, Yen-Jen Wang^*, Jianyu Chen

∗ Equal contribution. Listed alphabetically.

ICRA Workshop on Agile Robotics, 2024

Paper Code Project Page Video

See all publications →

Recent News

Selected Awards

Selected Papers

VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes

Learning Dexterous Manipulation Skills from Imperfect Simulations

MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning

Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer