Juntao Ren Profile Picture
Email: renjt@stanford.edu

Juntao Ren

I am a PhD student at Stanford University. I enjoy thinking about how we can enable robots to learn and reason over time in the physical world. I am grateful to be supported by the Knight-Hennessy Fellowship and the NSF Graduate Research Fellowship.

I completed my undergrad in Computer Science and Mathematics at Cornell University, where I am grateful to have worked with Prof. Sanjiban Choudhury. I've also spent time at 1X Technologies working on World Models.

Please feel free to reach out!


Publications

* indicates equal contribution

SAILOR project animation

Arnav Kumar Jain*, Vibhakar Mohta*, Subin Kim, Atiksh Bhardwaj, Juntao Ren, Yunhai Feng, Sanjiban Choudhury, Gokul Swamy

In Submission, 2025.

TL;DR — We train both world and reward models from demonstration data, giving the agent the ability to reason about how to recover from mistakes at test time.

Juntao Ren, Priya Sundaresan, Dorsa Sadigh, Sanjiban Choudhury, Jeannette Bohg

International Conference on Robotics and Automation (ICRA), 2025.

TL;DR — We propose a unified action space by representing actions as 2D trajectories on an image, enabling robots to directly imitate from cross-embodiment datasets.

Hybrid IRL figure

Juntao Ren*, Gokul Swamy*, Steven Wu, Drew Bagnell, Sanjiban Choudhury

International Conference on Machine Learning (ICML), 2024.

TL;DR — We show that training on both expert and learning data can provably speed up interactive imitation learning in the absence of rewards, for both model-free and model-based algorithms.

MOSAIC project animation

Huaxiaoyue Wang*, Kushal Kedia*, Juntao Ren*, Rahma Abdullah, Atiksh Bhardwaj, Angela Chao, Kelly Y Chen, Nathaniel Chin, Prithwish Dan, Xinyi Fan, Gonzalo Gonzalez-Pumariega, Aditya Kompella, Maximus Adrian Pace, Yash Sharma, Xiangwan Sun, Neha Sunkara, and Sanjiban Choudhury

Conference on Robot Learning (CoRL), 2024.

TL;DR — We build a top-down modular system to allow for human-robot collaboration within the kitchen using high-level planners, low-level visuomotor policies, and human-motion forecasting.

Distribution Normalization figure

Yifei Zhou*, Juntao Ren*, Fengyu Li*, Ramin Zabih, Ser-Nam Lim

Neural Information Processing Systems (NeurIPS), 2023.

TL;DR — We prove that subtracting the mean of the image and language embeddings at test-time from each sample better aligns with the training-objective and improves performance.