Portrait
Jiaxing Li
Master Student
Harbin Institute of Technology, Shenzhen
About Me

I have a strong interest in multimodal AI and AI safety. I have previously worked on research in Autonomous Driving and AI Companion safety; currently, my main research focuses on World Models (the JEPA paradigm) and Brain Visual Decoding.

I am also an ACG enthusiast. I greatly enjoy games such as Project SEKAI, Fate/Grand Order, and Granblue Fantasy: Relink. Currently, I am also following the ongoing anime Bleach: Thousand-Year Blood War.

Education
  • Harbin Institute of Technology, Shenzhen
    Harbin Institute of Technology, Shenzhen
    Department of Electrical Engineering and Computer Science
    Master Student
    Sep. 2027 - present
  • Northeastern University
    Northeastern University
    Software Colledge
    Sep. 2023 - Jul. 2027
Honors & Awards
News
2026
I have been admitted as a graduate student to the Intelligent Science and Technology program at Harbin Institute of Technology, Shenzhen.
Sep 24
The work I completed during my internship at Zhejiang University, "COMPANIONSAFE: Assessing LLM Companion Safety from a User Perspective in Evolving Human-AI Relationships," has been accepted by IEEE S&P 2027, which accepted a total of 160 papers, with an acceptance rate of 15.8%.
Sep 14
My Second paper, "GEAR: From Dynamic Encoding to Dynamic Activation in Social Trajectory Prediction" has been accepted by ICDM 2026.
Aug 17
My first paper, "A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition" has been accepted by ACM MM 2026.
Jul 10
2025
As the team leader, I led my team members to win First Place in the National Grand Prize at the 2025 China Youth Science and Technology Innovation "Bidding for Leadership" Challenge of the 19th "Challenge Cup" National College Students' Extracurricular Academic Science and Technology Works Competition.
Oct 25
Selected Publications (view all )
CompanionSafe framework: dataset construction, relationship simulation, and safety evaluation
COMPANIONSAFE: Assessing LLM Companion Safety from a User Perspective in Evolving Human-AI Relationships

Shu Meng*, Haitao Xu*, Jiaxing Li, Ruixiang Hu, Shuai Hao, Chuan Yue, Wenrui Ma, Meng Han, Zhao Li (* equal contribution)

IEEE Symposium on Security and Privacy (S&P) 2027

CompanionSafe evaluates AI companion safety across four stages of evolving human-AI relationships and diverse user profiles. Its benchmark combines a taxonomy of 122 harmful behaviors with 610 evaluation questions to uncover stage-dependent risks and safety disparities across user groups.

[Paper]

CompanionSafe framework: dataset construction, relationship simulation, and safety evaluation
COMPANIONSAFE: Assessing LLM Companion Safety from a User Perspective in Evolving Human-AI Relationships

Shu Meng*, Haitao Xu*, Jiaxing Li, Ruixiang Hu, Shuai Hao, Chuan Yue, Wenrui Ma, Meng Han, Zhao Li (* equal contribution)

IEEE Symposium on Security and Privacy (S&P) 2027

CompanionSafe evaluates AI companion safety across four stages of evolving human-AI relationships and diverse user profiles. Its benchmark combines a taxonomy of 122 harmful behaviors with 610 evaluation questions to uncover stage-dependent risks and safety disparities across user groups.

[Paper]

GEAR architecture: generation-aware activation of self-motion and social-resonance biases
GEAR: From Dynamic Encoding to Dynamic Activation in Social Trajectory Prediction

Jiaheng Chen, Jiaxing Li, Leixia Wang#, Jianan Ju, Tinghe Zhang (# corresponding author)

IEEE International Conference on Data Mining (ICDM) 2026

GEAR introduces generation-aware, step-wise activation gates that dynamically modulate self-motion and social-resonance biases before final trajectory composition. It adapts the influence of individual motion and social interactions across future prediction steps and scene densities.

[Paper] [Code]

GEAR architecture: generation-aware activation of self-motion and social-resonance biases
GEAR: From Dynamic Encoding to Dynamic Activation in Social Trajectory Prediction

Jiaheng Chen, Jiaxing Li, Leixia Wang#, Jianan Ju, Tinghe Zhang (# corresponding author)

IEEE International Conference on Data Mining (ICDM) 2026

GEAR introduces generation-aware, step-wise activation gates that dynamically modulate self-motion and social-resonance biases before final trajectory composition. It adapts the influence of individual motion and social interactions across future prediction steps and scene densities.

[Paper] [Code]

INTraJ architecture: explicit planning and reaction decomposition
A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition

Jiaheng Chen, Jiaxing Li, Tinghe Zhang, Chaopeng Guo# (# corresponding author)

ACM International Conference on Multimedia (ACM MM) 2026

INTraJ decomposes social influence in trajectory prediction into planning and reaction: anticipating others' future behavior to construct reference trajectories, then recovering local reactive adjustments. The unified framework supports both multi-target and single-target prediction.

[Paper] [DOI] [Code]

INTraJ architecture: explicit planning and reaction decomposition
A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition

Jiaheng Chen, Jiaxing Li, Tinghe Zhang, Chaopeng Guo# (# corresponding author)

ACM International Conference on Multimedia (ACM MM) 2026

INTraJ decomposes social influence in trajectory prediction into planning and reaction: anticipating others' future behavior to construct reference trajectories, then recovering local reactive adjustments. The unified framework supports both multi-target and single-target prediction.

[Paper] [DOI] [Code]

All publications