About

I am a graduate student in Electrical and Computer Engineering at Georgia Tech. My work focuses on building reliable and data-efficient AI systems with strong representation learning.

My research focuses on reliable and data-efficient AI systems, with an emphasis on representation learning and controllability. I am broadly interested in methods that enable robust generalization and efficient adaptation in interactive and language-based settings.

Research Focus

  • LLM persona icon

    LLM Persona Modeling

    Understanding and controlling persona-level representations in LLMs.

  • World model icon

    World Models

    Learning predictive world models for robust embodied intelligence.

  • Hashing icon

    Semantic Hashing

    Learning compact semantic representations for efficient retrieval.

  • System icon

    Robust AI Systems

    Building AI systems that remain reliable under distribution shift.

Selected Publications

  1. X Ma, R Li, X Zhang, Z Weng. "UniHash: Unifying Pointwise and Pairwise Hashing Paradigms for Seen and Unseen Category Retrieval."

    arXiv preprint, 2026

    Archive

  2. X Ma, X Zhang, Z Weng. "Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activations."

    arXiv preprint, 2026

    Archive

  3. G Zollicoffer, T Chopra, M Yan, X Ma, K Eaton, M Riedl. "World Model Robustness via Surprise Recognition."

    arXiv preprint, 2025

    Archive

  4. C Ye, S Shang, X Ma, X Zhang. "Input-Envelope-Output: Auditable Generative Music Rewards in Sensory-Sensitive Contexts."

    CHI 2026 (Accepted)

    Archive: to be released.

Academic Service

Reviewer: ACL Rolling Review (ARR), January 2026

Mentoring: I am happy to advise students from underrepresented backgrounds on graduate applications, research planning, and academic growth.

Publications

Conference and Journal Papers

  1. Shuquan Man, Qiulin Chen, Xiaoxu Ma. "Research and application of time series prediction model based on prophet algorithm."

    2023 IEEE 5th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), 2023

    Archive

  2. X Ma, R Li, X Zhang, Z Weng. "UniHash: Unifying Pointwise and Pairwise Hashing Paradigms for Seen and Unseen Category Retrieval."

    arXiv preprint, 2026

    Archive

  3. X Ma, X Zhang, Z Weng. "Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activations."

    arXiv preprint, 2026

    Archive

  4. X Ma, R Li, Z Weng. "Mutual Learning for Hashing: Unlocking Strong Hash Functions from Weak Supervision."

    arXiv preprint, 2025

    Archive

  5. G Zollicoffer, T Chopra, M Yan, X Ma, K Eaton, M Riedl. "World Model Robustness via Surprise Recognition."

    arXiv preprint, 2025

    Archive

  6. R Li, X Ma, Z Weng, Y Zhang, G Luo, H Zhuang, Z Lin, YP Tan. "Unsupervised Data-Efficient Cross-Modal Retrieval with Global-Neighborhood Alignment Hashing."

    Under Review

    Archive: to be released.

  7. C Ye, S Shang, X Ma, X Zhang. "Input-Envelope-Output: Auditable Generative Music Rewards in Sensory-Sensitive Contexts."

    CHI 2026 (Accepted)

    Archive: to be released.

Resume

Education

  1. M.S. in Electrical and Computer Engineering, Georgia Institute of Technology

    08/2025 — Present

    Department of Electrical and Computer Engineering (ECE).

  2. Exchange Student, Electrical and Computer Engineering, Technical University of Munich

    04/2024 — 10/2024

    Participated in ECE exchange program with coursework and research exposure.

  3. B.Eng. in Robotics Engineering, South China University of Technology

    09/2021 — 06/2025

    Robotics Engineering program with a focus on intelligent systems and automation.

Experience

  1. Research Assistant, Georgia Institute of Technology

    09/2025 — Present

    Working on persona-level modeling in large language models and world models for embodied intelligence, with an emphasis on representation learning and robustness.

  2. Research Assistant, Shien-Ming Wu School of Intelligence Engineering, SCUT

    10/2024 — 08/2025

    Conducted research on image retrieval, focusing on representation learning and efficient similarity search methods.

  3. Head Teaching Assistant, Introduction to Circuits, Future Technology Institute, SCUT

    09/2024 — 02/2025

    Served as Head TA for Introduction to Circuits at the Future Technology Institute, coordinating TA team operations, supporting labs and assignments, managing grading, and assisting course instruction for undergraduate students.

  4. Robotics Tutor, Education Department, SCUT Robotics Association

    11/2021 — 09/2023

    Served as a robotics tutor in the Education Department of the SCUT Robotics Association, delivering robotics instruction to junior undergraduate students and middle school students, and supporting hands-on learning in robotics fundamentals.

Skills

Programming: Python · PyTorch · NumPy / SciPy · CUDA · C / C++

Tools & Systems: Linux · Git · Slurm / HPC · Docker · LaTeX

Teaching & Communication: Robotics Tutoring · Academic Writing · Research Presentation · Cross-cultural Communication