Ziyang Liu

Academic and Career Interests: As an undergraduate student graduating in 2026, I am seeking to pursue graduate studies (Master's/Ph.D.) in Artificial Intelligence, Multimodal Analysis, and Statistical Analysis. I warmly welcome discussions with professors and industry professionals. If you are interested in my research direction or experience, please feel free to contact me via email or WeChat.

Personal Introduction

I am an undergraduate student majoring in Statistics at Soochow University and a member of the Tsinghua University Qian Xuesen Class & X Institute Joint Training Program. My research interests primarily focus on artificial intelligence and multimodal sentiment analysis, with particular attention to AI applications in social innovation. In academic research, I have published papers in CCF-A/B conferences and obtained multiple patents. Additionally, I actively participate in various mathematical modeling competitions, dedicated to combining theoretical knowledge with practical applications.

Education

Undergraduate: School of Future Science and Engineering, Soochow University Statistics Major, 2022.09-2026.06

GPA: 3.8/4.0, 90/100, Rank: 3/65, Top 5% in Major
Key Courses: Mathematical Analysis, Advanced Algebra, Applied Multivariate Analysis, Probability Theory and Mathematical Statistics, Python Programming, Mathematical Modeling and Software
English Proficiency: TOEFL, CET-6

Joint Training: Tsinghua University Qian Xuesen Class - X Institute, 2024.09-2026.09

Research Direction: Artificial Intelligence
Key Programs: ESRT, ORIC, SURF See Qian Class Training Program
Mentors: Min Tang (Former State Council Counselor), Yang Liu (Assistant Professor, National University of Singapore)

Research Projects

Multimodal Sentiment Analysis Project, School of Computer Science and Technology, Soochow University (Project Leader, 2024.02-2025.03)

Research Focus: Utilizing multimodal data (text, video, audio) for sentiment analysis, with special attention to robustness improvement in cases of partial modality missing
Key Contribution: Proposed the Factor-based Semantic Recovery Framework (FSRF), achieving SOTA performance on multiple benchmark datasets
Applications: Social media sentiment analysis, intelligent customer service, user experience analysis

Multi-Agent Reinforcement Learning Project, Department of Electronic Engineering, Tsinghua University (Core Member, 2025.04-2025.06)

Project Description: Focus on collaborative optimization and reinforcement learning of multi-agent systems under complex tasks
Main Work: Construct multi-agent interaction framework, design task environments and implement coordination mechanisms between agents
Technical Contribution: Combined Test-Time Reinforcement Learning (TTRL) for policy training, effectively improving system generalization performance
Research Achievements: Independently completed code module development and debugging, assisted in structural analysis and convergence derivation of TTRL theoretical mechanisms

Tsinghua University - Shenzhen X Institute ESRT Project: Research and Implementation of AI Agent System for Intelligent Interaction (Project Leader, 2024.10-2025.02)

Project Content: Development of intelligent agents supporting text and voice interaction, achieving task automation and multimodal content generation
Technical Implementation: Participated in developing WeChat chatbot "Giiso_Wechat", integrating various APIs for intelligent interaction

Student Innovation Project: HeartSync - AI-Powered Emotional Support System for Left-behind Children (Project Leader, 2024.06-2024.12)

Project Overview: Development of AI-based personalized emotional support and psychological counseling system for left-behind children
Achievements: Won the 2024 X Institute Excellence Project Award and National College Student Innovation Competition Third Prize

Published Papers

ICME 2025（Oral）: "FSRF: Factorization-guided Semantic Recovery for Incomplete Multimodal Sentiment Analysis" (CCF-B, First Author) (Click here to view)
CVPR 2025: "MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation" (CCF-A, Second Author)
ICML 2025 (Workshop): "MERIT:Multimodal Emotion Recognition via RL-Enhanced Test-Time Adaptation" (CCF-A, Corresponding Author) (Click here to view)
ICIRDC 2024: "Establishment and solution of a multi-stage decision model based on hypothesis testing and dynamic programming algorithm" (EI, First Author) (Click here to view)

Internship Experience

Shenzhen X Institute (Teaching Assistant, 2025.07-2025.08): Assisted professors in completing course teaching work
ByteDance (Training Program, 2025.02-2025.04): Participated in AI-driven memoir writing assistance project for the elderly (Function Introduction Video)
Tsinghua Shenzhen International Graduate School (Research Intern, 2025.01-2025.02): Assisted in integrating GeWechat with Restful API, developing customized chatbots with text and voice interaction capabilities (Function Demo Video)

Competition Awards

2025 The 21st Baidu Star Programming Contest Preliminary: Gold Award (View Certificate)
2025 The 7th MaTiBei Programming Contest: Gold Award (5th in Jiangsu Province) (View Certificate)
2025 Mathematical Contest in Modeling (MCM): Meritorious Winner (Team Leader) (View Certificate)
2025 Blue Bridge Cup Python Group A: Jiangsu Province Second Prize (View Certificate)
2024 National College Student Innovation Competition: National Third Prize (Team Leader) (View Certificate)
2024 Huashu Cup China Undergraduate Mathematical Contest in Modeling: First Prize (Team Leader) (View Certificate)
2024 China Undergraduate Mathematical Contest in Modeling: Jiangsu Province First Prize (Team Leader) (View Certificate)
2024 Mathematical Contest in Modeling (MCM): Honorable Mention(Team Leader) (View Certificate)
2024 National College Student Statistical Modeling Competition: Jiangsu Province Third Prize (Team Leader) (View Certificate)
2023 National Computer Rank Examination: Level 2 (MS Office Advanced Applications) (View Certificate)

About Shenzhen X Institute:

Shenzhen X Institute originates from Tsinghua University's "Xuetang Plan" Qian Xuesen Class (referred to as "Tsinghua Qian Class"). Tsinghua Qian Class was established in 2009 and is the only experimental class among the 66 pilot projects of the "Tsinghua Xuetang Talent Training Plan" and the national "Basic Discipline Top Student Training Experimental Plan" that is not positioned for a single discipline, but for engineering foundation (or interdisciplinary innovation of mechanics and engineering technology). Its mission is to discover and cultivate innovative talents who aspire to change the world and benefit humanity through technology, explore future innovative talent training models, and answer "Qian Xuesen's Question".

Outstanding Course Grades

Mathematics Courses:
- Mathematical Analysis III: 94/100
- Advanced Algebra I: 92/100
- Probability Theory and Mathematical Statistics I: 96/100
- Complex Function Theory II: 95/100
Statistics and Data Analysis Courses:
- Qualitative Data Analysis: 95/100
- Applied Time Series: 97/100
- Applied Regression Analysis: 96/100
- Applied Multivariate Analysis: 94/100
- Statistical Computing and SAS Software (Bilingual): 95/100
Computer Science and Programming Courses:
- Computer Information Technology (Computational Thinking): 94/100
- Python Programming: 94/100
Interdisciplinary Courses:
- Introduction to Finance: 94/100
- Taoist Culture and Wellness Wisdom: 96/100