Ruochen Jiao

PhD candidate, Computer Engineering, Northwestern University Evanston, IL, U.S. Email: ruochen.jiao@u.northwestern.edu My name in Chinese is 焦若辰

I am an applied scientist at Amazon working on foundational AI models. I received my Ph.D. in Computer Engineering at Northwestern University, advised by Prof. Qi Zhu. I also work close with Prof. Alfred Chen. Prior to Northwestern, I received my B.S. in Electrical Engineering from Zhejiang University in 2019.

The long-term goal of my research and work is to build trustworthy (embodied) AI agents. My research interests include robust and explainable ML, large language models (LLMs), and behavior modeling/decision-making.

Education

Northwestern University: Ph.D. in Computer Engineering, 2019 - 2024

Zhejiang University: B.S. in Electrical Engineering, 2019

News

• June 2024   Our paper Kinematics-aware Trajectory Generation and Prediction with Latent Stochastic Differential Modeling has been accepted by IROS 2024.

• May 2024   Our recent preprint on backdoor attacks against LLM-based decision-making is available online.

• Mar 2024   Our paper Empowering Autonomous Driving with Large Language Models: A Safety Perspective has been accepted to LLMAgents @ ICLR 2024.

• Nov 2023   We have a few preprints on physics-informed motion generation, the large language models (LLMs) for autonomous driving, and safe RL with image observations

• Aug 2023   The co-authored book chapter "Safety-Assured Design and Adaptation of Connected and Autonomous Vehicles" is now available online.

• July 2023   Our paper Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction has been accepted by ICCV 2023!

• June 2023   Our two papers have been accepted by IROS 2023!

• June 2023   I will join Amazon as an Applied Scientist intern.

• April 2023   Our paper Enforcing Hard Constraints with Soft Barriers: Safety-driven Reinforcement Learning in Unknown Stochastic Environments has been accepted by ICML 2023.

• Feb. 2023   Our paper Efficient Stuttering Event Detection Using Siamese Networks has been accepted by ICASSP 2023.

• June 2022   Our paper TAE: A Semi-supervised Controllable Behavior-aware Trajectory Generator and Predictor has been accepted by 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022).

• Feb. 2022   Our paper Neural Network based Interactive Lane Changing Planner in Dense Traffic with Safety Guarantee has been accepted by ASP-DAC 2023.

• June 2021   I will join the InfoTech Labs Toyota as a research scientist intern and work on mobile vehicular cloud.

• May 2021   Our paper End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering has been accepted by the 32th IEEE Intelligent Vehicles Symposium (IV21).

• Feb 2021   Our paper WIP: End-to-end analysis of adversarial attacks to automated lane centering systems has been accepted by the 2021 Automotive and Autonomous Vehicle Security (AutoSec) Workshop and awarded best short paper.

Selected Publications

• Exploring Backdoor Attacks against Large Language Model-based Decision Making.   paper

  • Ruochen Jiao*, Shaoyuan Xie*, Justin Yue, Takami Sato, Lixu Wang, Yixuan Wang, Qi Alfred Chen, Qi Zhu

  • under review

• Kinematics-aware Trajectory Generation and Prediction with Latent Stochastic Differential Modeling.  paper

  • Ruochen Jiao*, Yixuan Wang*, Xiangguo Liu, Simon Zhan, Chao Huang, Qi Zhu

  • IROS 2024

• State-wise Safe Reinforcement Learning With Pixel Observations.  paper

  • Sinong Simon Zhan, Yixuan Wang, Qingyuan Wu, Ruochen Jiao, Chao Huang, Qi Zhu

  • L4DC 2024

• Empowering Autonomous Driving with Large Language Models: A Safety Perspective.  paper

  • Yixuan Wang*, Ruochen Jiao*, Chengtian Lang, Sinong Simon Zhan, Chao Huang, Zhaoran Wang, Zhuoran Yang, Qi Zhu

  • LLMAgents ICLR 2024

• Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction.   paper

  • Ruochen Jiao, Xiangguo Liu, Takami Sato, Alfred Chen, Qi Zhu

  • ICCV 2023

• Learning Representation for Anomaly Detection of Vehicle Trajectories.  paper

  • Ruochen Jiao, Juyang Bai, Xiangguo Liu, Takami Sato, Xiaowei Yuan, Alfred Chen, Qi Zhu

  • IROS 2023

• Safety-Assured Speculative Planning with Adaptive Prediction.   paper

  • Xiangguo Liu, Ruochen Jiao, Yixuan Wang, Yimin Han, Bowen Zheng, Qi Zhu

  • IROS 2023

• Enforcing Hard Constraints with Soft Barriers: Safety-driven Reinforcement Learning in Unknown Stochastic Environments.  paper

  • Yixuan Wang, Simon Zhan, Ruochen Jiao, Zhilu Wang, Wanxin Jin, Zhuoran Yang, Zhaoran Wang, Chao Huang, Qi Zhu

  • ICML 2023

• TAE: A Semi-supervised Controllable Behavior-aware Trajectory Generator and Predictor.  paper

  • Ruochen Jiao, Xiangguo Liu, Bowen Zheng, Dave Liang, Qi Zhu

  • IROS 2022

• Safety-driven Interactive Planning for Neural Network-based Lane Changing.   paper

  • Xiangguo Liu, Ruochen Jiao, Bowen Zheng, Dave Liang, Qi Zhu

  • ASP-DAC 2023, Best Paper Candidate

• End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering.  paper

  • Ruochen Jiao*, Hengyi Liang*, Takami Sato, Junjie Shen, Alfred Chen, Qi Zhu

  • IV 2021

• WIP: End-to-end analysis of adversarial attacks to automated lane centering systems.   paper

  • Hengyi Liang*, Ruochen Jiao*, Takami Sato, Junjie Shen, Alfred Chen, Qi Zhu

  • AutoSec 2021, Best Short Paper Award

• Safety-assured design and adaptation of learning-enabled autonomous systems.   paper

  • Qi Zhu, Chao Huang, Ruochen Jiao, Shuyue Lan, Hengyi Liang, Xiangguo Liu, Yixuan Wang, Zhilu Wang, Shichao Xu

  • ASP-DAC 2021

• Leveraging weakly-hard constraints for improving system fault tolerance with functional and timing guarantees.   paper

  • Hengyi Liang, Zhilu Wang, Ruochen Jiao, Qi Zhu

  • ICCAD 2020

Experience

Applied scientist intern, Amazon, Seattle, supervised by Binchao Chen, Jun. 2023 - Sep. 2023

Research scientist intern, InfoTech Labs, Toyota, Mountain View, supervised by Onur Altintas, Jun. 2021 - Sep. 2021

Big data engineer, Intel, Shanghai, Mar. 2019 - Jun. 2019

Service

Reviewer   ECCV, IROS, ICRA, Neurips, ICLR, AISTATS, IV, RA-L, TMM, TNNLS, TCAD, TCPS, TIV, IEEE JSAC