Ruiqian Nai 佴瑞乾

I am a third-year PhD student at the Institute for Interdisciplinary Information Sciences, Tsinghua University, advised by Prof. Yang Gao. Previously, I earned my B.S. degree from the Department of Automation, Tsinghua University.

My research focuses on advancing embodied intelligence—enabling robots to perceive, reason, and learn through cutting-edge machine learning technologies. I believe that the pursuit of embodied intelligence involves a cycle of understanding, reasoning, and reinforcement learning. Agents first acquire knowledge from data, make decisions based on this knowledge, and continuously improve through their own experiences.

Email  /  Scholar  /  Twitter  /  Github

Selected Publications (* indicates equal contribution)

We introduce OneTwoVLA, a single unified vision-language-action model capable of both acting (System One)⚡ and reasoning (System Two)🤔. Importantly, it adaptively determines when to engage each mode.

We propose HuB (Humanoid Balance) 🤖, a framework that enables humanoids to perform challenging quasi-static balance tasks ⚖️, including extreme single-legged poses 🦵 such as the Swallow Balance 🕊️ and Bruce Lee's Kick 🦶🥋.

Better locomotion using real-world data. Our approach achieves a 24-28% net reduction in power consumption 🔋.

We show that informativeness 🧠 is a more crucial factor than disentanglement 🌀 in downstream tasks.

Modified from Jon Barron's website.