Headshot of Kyle Hsu

Kyle Hsu

徐宏愷

Senior ML Engineer, Tesla Optimus

kylehsu@cs.stanford.edu

I work on AI for Optimus at Tesla. My contributions span the learning stack: data, deployment & evals, pre- & post-training, and sim ⇄ real.

My PhD at Stanford was advised by Chelsea Finn and Jiajun Wu. Several of my projects tackled key ingredients of modern robot learning: effective data collection via wrist cameras, reliable sim evals, and visual tokenization for scaling policy pre-training.

I'm a bilingual Taiwanese-Canadian. In my free time, I like to ski/snowboard and play games, especially Soulslikes.

selected publications

robot learning

Vision-based manipulators need to also see from their hands
Kyle Hsu*, Moo Jin Kim*, Rafael Rafailov, Jiajun Wu, Chelsea Finn
ICLR 2022 oral
paper project page
Evaluating real-world robot manipulation policies in simulation
Xuanlin Li*, Kyle Hsu*, Jiayuan Gu*, Karl Pertsch, Oier Mees, Homer Rich Walke, Chuyuan Fu, Ishikaa Lunawat, Isabel Sieh, Sean Kirmani, Sergey Levine, Jiajun Wu, Chelsea Finn, Hao Su, Quan Vuong, Ted Xiao
CoRL 2024
DGR@RSS2024 spotlight
paper project page

representation learning

Disentanglement via latent quantization
Kyle Hsu, Will Dorrell, James CR Whittington, Jiajun Wu, Chelsea Finn
NeurIPS 2023
paper poster code
Flow to the mode: mode-seeking diffusion autoencoders for state-of-the-art image tokenization
Kyle Sargent, Kyle Hsu, Justin Johnson, Li Fei-Fei, Jiajun Wu
ICCV 2025
paper project page

few-shot learning

Unsupervised learning via meta-learning
Kyle Hsu, Sergey Levine, Chelsea Finn
ICLR 2019
paper project page
FSPO: few-shot optimization of synthetic preferences personalizes to real users
Anikait Singh*, Sheryl Hsu*, Kyle Hsu, Eric Mitchell, Stefano Ermon, Tatsunori Hashimoto, Archit Sharma, Chelsea Finn
ICLR 2026
paper project page

scalable abstraction-based controller synthesis

Multi-layered abstraction-based controller synthesis for continuous-time systems
Kyle Hsu, Rupak Majumdar, Kaushik Mallik, Anne-Kathrin Schmuck
HSCC 2018
paper code
Lazy abstraction-based controller synthesis
Kyle Hsu, Rupak Majumdar, Kaushik Mallik, Anne-Kathrin Schmuck
ATVA 2019 invited paper
paper code