Zhenjiang Mao

Ph.D. Student.
Department of Electrical & Computer Engineering, University of Florida.
Email: z.mao@ufl.edu
About me

I'm currently a Ph.D. Student at The Department of Electrical & Computer Engineering at the University of Florida, supervised by Dr. Ivan Ruchkin who lead the Trustworthy Engineered Autonomy (TEA) Lab . I was tempororily in master program of Electrical and System Engineering at University of Pennsylvania. I received my B.S. degree in from Southern University of Science and Technology, China, where I was also a member of Pan Group@SUSTech , supervised by Dr. Quan Pan who lead high-speed communication interface study. I used to be a member in Brain-inspired Computing Lab in Guangzhou Campus of Hong Kong University of Science and Technology (HKUST,GZ) for an internship with research direction of application of spiking neural network (SNN) and event camera, supervised by Dr. Renjing Xu.

Research Interests:
  • Safe and Trustworthy Autonomous Systems: Modeling, analysis, monitoring and prediction; Confidence measurement
  • Time Sequence Prediction and Uncertainty Quantification: with ML/AI and foundation models (LLMs, VLMs and VLAs)
  • Representation Learning and Agentic AI: Casual/Physical-interpretable representation learning; World models

News
  • [Pinned] I am actively seeking to collaborate with researchers from a wide array of disciplinary backgrounds. My goal is to transcend the limitations imposed by conventional disciplinary paradigms by leveraging interdisciplinary perspectives. If you're intrigued by the prospect of working together to tackle complex problems through a multifaceted approach, I warmly invite you to reach out. Your expertise and insights could play a crucial role in our collective endeavor. Please don't hesitate to contact me if you're interested in exploring this collaborative opportunity further.
  • [2026] Our paper "Anomaly-Informed Confidence Calibration for Vision-Based Safety Prediction" by Zhenjiang Mao, Jiawen Wu, Gabriel Wagner and Ivan Ruchkin has been submitted to the 2026 IEEE International Conference on Intelligent Robots and Systems (IROS), Pittsburgh, PA, USA. (Under Review)
  • [2026] Our paper "Physically Interpretable World Models via Weakly Supervised Representation Learning" by Zhenjiang Mao, Mrinall Eashaan Umasudhan and Ivan Ruchkin has been accepted to HSCC & ICCPS '26: 29th ACM International Conference on Hybrid Systems: Computation and Control, and 17th ACM/IEEE International Conference on Cyber-Physical Systems (with CPS-IoT Week, Saint Malo, France, 2026).
  • [2026] Our paper "Confidence over Time: Confidence Calibration with Temporal Logic for Large Language Model Reasoning" by Zhenjiang Mao, et al. has been submitted to ACL 2026. (Under Review)
  • [2026] Our paper "Recurrent Confidence Chain: Temporal-Aware Uncertainty Quantification in Large Language Models" by Zhenjiang Mao, et al. has been accepted to ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2026.
  • [2025/05] Our paper "Temporalizing Confidence: Signal Temporal Logic Evaluation of Multi-Step Chain-of-Thought Reasoning" by Zhenjiang Mao, Rohith Reddy Nama, Artem Bisliouk, and Ivan Ruchkin has been accepted to the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025) at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), Vienna, Austria, 2025.
  • [2025/05] Our paper "Principles for Physically Interpretable World Models" has been accepted by International Conference on Neuro-symbolic Systems (NeuS), Philadelphia, PA, 2025.
  • [2025/04] Our work "Four Principles for Physically Interpretable World Models" will be presented as a latest breakthrough at FMNS ICRA 2025 Workshop on Foundation Models and Neuro-Symbolic AI for Robotics in Atlanta.
  • [2025/03/15] Three new preprints: generalizable image repair , principles for interpretable world models , physically interpretable world models
  • [2025/02] Invited talk at Brown Bag Seminar at UF: "Uncertainty in World Models for Learning Dynamics and Environments in Autonomous Systems"
  • [2024/10/04] Invited talk at 2nd International Workshop on Trustworthy Autonomous Cyber-Physical Systems (Raleigh, NC): "How Safe Will I Be Given What I See? Calibrated Visual Safety Chance Prediction with (Foundation) World Models"
  • [2024/05] Two workshop presentations at ICRA 2024:
    • Robot Learning Going Probabilistic Workshop: "Zero-shot Safety Prediction for Autonomous Robots with Foundation World Models"
    • Robot Trust for Symbiotic Societies (RTSS) Workshop: "Language-Enhanced Latent Representations for Out-of-Distribution Detection in Autonomous Driving"
  • [2024/03] Invited talk at Brown Bag Seminar at UF: "How safe am I given what I see? calibrated prediction of safety chances for image-controlled autonomy"
  • [2024/04/09] One paper workshop paper has been accepted by ICRA 2024 Workshop — Back to the Future: Robot Learning Going Probabilistic.
  • [2024/04/02] One paper on Calibrated Safety Prediction has been accepted by 6th Annual Learning for Dynamics & Control Conference.


Publications [Google Scholar here]
2026
  • [Under Review] Zhenjiang Mao, Jiawen Wu, Gabriel Wagner and Ivan Ruchkin.
    Anomaly-Informed Confidence Calibration for Vision-Based Safety Prediction.
    Submitted to 2026 IEEE International Conference on Intelligent Robots and Systems (IROS), Pittsburgh, PA, USA.
  • [Conference] Zhenjiang Mao, Mrinall Eashaan Umasudhan and Ivan Ruchkin.
    Physically Interpretable World Models via Weakly Supervised Representation Learning.
    HSCC & ICCPS '26: 29th ACM International Conference on Hybrid Systems: Computation and Control, and 17th ACM/IEEE International Conference on Cyber-Physical Systems (with CPS-IoT Week, Saint Malo, France, 2026).
  • [Under Review] Zhenjiang Mao, et al.
    Confidence over Time: Confidence Calibration with Temporal Logic for Large Language Model Reasoning.
    ACL 2026.
  • [Conference] Zhenjiang Mao, et al.
    Recurrent Confidence Chain: Temporal-Aware Uncertainty Quantification in Large Language Models.
    ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2026.
2025

2024


Ongoing Projects
  • Hallucination Detection in Video Foundation Models: Developing a unified hallucination detection framework for state-of-the-art text-to-video generative models (e.g., Wan, Hunyuan Video). The project focuses on multimodal consistency checking, motion/physics violation detection, and reference-free evaluation metrics for identifying temporal and spatial hallucinations in generated videos.
  • Uncertainty Quantification & Calibration in Large Foundation Models: Investigating confidence estimation, temporal uncertainty modeling, and calibration techniques for LLMs and VLMs. The project aims to build reliable uncertainty-aware reasoning pipelines for different tasks and multimodal understanding.
  • Reliable World Models for Autonomous Systems: Building reliable world models by integrating formal verification and calibration methods to ensure consistent dynamics prediction, robustness under distribution shifts, and trustworthy deployment.


Honors and Awards
  • Innovate Award by UF Innovate at Annual Nelms IoT Conference 2026 for Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic
  • Most Innovative Solution Award at the 2025 AWS & Vanderbilt Mission Autonomy Hackathon
  • Second Place at the Poster Competition on Warren B. Nelms Annual IoT Conference 2024 for Zero-shot Safety Prediction for Autonomous Robots with Foundation World Models
  • Future Star Award of 2021 EdgeX Edge Computing Competition hosted by Linux Foundation
  • Second place in the Embedded System and Deep Learning Competition of the Summer Exchange Program at the School of Computing at the National University of Singapore (NUS), 2021
  • Third Place in Remote Control Concrete Boat Building and Racing: China Dragon Boat Festival Competition, 2021
  • Second place in the mysterious application, Third place in the HPL benchmark at SC20 International College Student Supercomputer Competition
  • Bronze Award of 2020 Guangdong Province Challenge Cup Innovation and Entrepreneurship Competition
  • Freshman Scholarship (2018), Second-class(2019) and First-class (2020) of the Merit Student Scholarship
  • Outstanding Volunteer(2019), Outstanding Student Leader(2020), Academic Star(2021) of SUSTech
  • Bronze Award of 2016 National Youth Science and Technology Innovation Competition


Community Services
  • Reviewer for The IEEE Robotics and Automation Letters
  • Subreviewer for IEEE Space Mission Challenges for Information Technology and Space Computing Conference (SMC-IT/SCC), 2024
  • External Reviewer for 15th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), 2024
  • External Reviewer for International Conference on Artificial Intelligence and Statistics (AISTATS), 2025
  • External Reviewer for 20th International Conference on Software Engineering for Adaptive and Self-Managing Systems


Talks
  • 2025 Brown Bag Seminar at UF: Uncertainty in World Models for Learning Dynamics and Environments in Autonomous Systems, 2025
  • 2024 Brown Bag Seminar at UF: How safe am I given what I see? calibrated prediction of safety chances for image-controlled autonomy, 2024
  • 2nd International Workshop on Trustworthy Autonomous Cyber-Physical Systems: How Safe Will I Be Given What I See? Calibrated Visual Safety Chance Prediction with (Foundation) World Models, at Raleigh, NC, October 4, 2024.
  • Robot Learning Going Probabilistic Workshop at ICRA 24: Zero-shot Safety Prediction for Autonomous Robots with Foundation World Models
  • Robot Trust for Symbiotic Societies (RTSS) Workshop at ICRA 24: Language-Enhanced Latent Representations for Out-of-Distribution Detection in Autonomous Driving


Work Experience
  • 2022.03-2022.07, Guangzhou, China.
  • 2021, Shenzhen, China.
  • 2022, Shenzhen, China.
  • 2021, Shenzhen, China.
  • 2020, Shenzhen, China.


Teaching and Mentoring Experience
  • 24 Spring, EGN 4912 Reliable and Safe Autonomous Racing (graduate meta-mentor)
  • 24 Fall, CIS 4914 Senior Design: Trajectory Prediction
  • 23 Summer, The Summer Undergraduate Research at Florida (SURF) Program: Mentoring 2 Undergraduate Students from Shandong University and Shanghai University
  • 23 Spring and 23 Fall: Mentoring 2 master students at UF to run HSAI models on donkey car


Skills Summary
  • Programming Languages: Fluent: Python, Java; Proficient: C, Rust, Go, Matlab, JavaScript, SQL, Linux scripting
  • Software/Tools: Cadence, Docker, Git, SpringBoot, Linux system, Microsoft Office, Origin, SolidWorks, AutoCAD, Cisco Packet Tracer, Wireshark
  • Computer-related Capabilities: Data processing analysis and visualization, Server operation and maintenance, Supercomputer multi-node parallel computing, Software development, Deep learning (with PyTorch and tensorflow)
  • Hardware: Ultra-high-speed hybrid IC design, SolidWorks-based model laser cutting and 3D printing/construction
  • Cloud Services: AWS EC2, Lambda, DynamoDB, API Gateway, CloudFront, S3, Cognito, IoT Core & Greengrass
  • AI (LLM) Agent: LangChain/LangSmith, AWS Bedrock & SageMaker, Cloudflare AI Worker, OpenAI Assistants API


Miscellaneous
  • Language: English - fluent, Mandarin (Chinese) - native, Cantonese (Chinese) - medium, Japanese - basic
  • Memberships: IEEE student member, ACM student member, IEEE Robotics and Automation Society student member