Fangyanuo Zhou – Research

Publications

Patents

Research Experience

Focus: Interdisciplinary research at the intersection of news communication and large models, including LLM value alignment, multimodal fake news detection, multi-task fake news detection models, agent-based fake news dissemination simulation, sentiment analysis, hallucination research, and text readability analysis. It also includes recommender-system-related fake news studies, such as text-level comparisons between generative recommender systems and traditional recommender systems, and the propagation effects of fake news within recommender systems.

Responsibilities:

• Core work: Built an agent-based simulation for the news dissemination process, designed intervention and ablation experiments, and implemented a multi-task fake news detection model.
• Supporting work: Investigated differences in value alignment between generative recommender systems and traditional recommender systems. Studied whether fake news generated by large models, after passing through recommender systems, may lead to truth decay. Used Python for web crawling on domestic and international news websites, leveraged large models for batch summarization and value system analysis, ran batch experiments via external APIs, explored diverse neural network frameworks and popular deep learning architectures, and contributed to research background and related knowledge sections in papers.
• Competition: Participated in a social simulation competition, contributing to prompt design and cloud-based distributed deployment.

Achievements:

• Co-authored a multimodal MoE fake news detection paper accepted by IEEE TCE (doi: 10.1109/TCE.2026.3677445).
• Co-authored “Towards Better Transparency and Reliability in Smart Contract Vulnerability Detection via Counterfactual Contrastive Explanations” (Y.-Y. Shi, F. Zhou, Y.-K. Wang, Q.-Y. Zou, H.-J. Song), under review, and a multi-task fake news detection paper in progress.
• Tourism trajectory simulation and visitor-flow prediction study for travel routes, in progress.
• Open-source outputs: WeSpeak, Reptile. Patent pending (expected approval in 2026.9 – 2026.10).

Introduction: Developing a multimodal AI psychological coaching system for college students, with a rigorous randomized controlled trial to evaluate its causal intervention effect on students’ mental health. The project integrates large language models, multimodal perception technology, and evidence-based psychological intervention methods.

Responsibilities:

• Developed a Linux-deployed AI coaching system integrating multiple RAG knowledge bases and MCP-based tool interfaces.
• Contributed to the randomized controlled trial design evaluating the causal effects of AI-assisted interventions on university students’ mental health.
• Contributed to system implementation and manuscript preparation.

Achievements: Connected with senior students in the group and kept the collaboration going, and gained experience working in a cross-functional, highly structured team.

Introduction: Built generative AI to produce structured medical records, reducing repetitive work, delays, and quality inconsistency. Focused on medical dialogue modeling to enable automatic outpatient record generation.

Responsibilities:

• Early-stage speech-to-text (Whisper), Qwen fine-tuning, and prompt engineering. As a core developer, iterated on models to improve the standardization and practicality of generated medical records.
• Batch data testing and effect tuning by building automated test pipelines, significantly improving testing efficiency.
• Assisted environment deployment, local proxy setup, and firewall access.

Achievements: The project later shifted to mental health departments with potential hospital adoption in Guangzhou. Learned how products in smart healthcare are thought through and where their domain constraints sit, and built the habit of making a system technically strong while keeping it safe and robust. Also strengthened cross-functional collaboration, reporting, progress management, and Linux development skills.

Introduction: Built a visitor behavior simulation platform using Python and Vue with official platform data plus web-crawled data, exploring social media impact on travel route choices.

Responsibilities: Implemented time filtering and improved data visualization modules. Delivered key functions such as multi-day repeated population addition and temporary scenic spot closure.

Achievements: Expected to publish at least one paper (target submission before 2026.12). Strengthened complex software system development and high-standard delivery capability.

Introduction: Applied computer vision to evaluate livestock breeding effects, built a custom data annotation platform, and trained YOLO models for target weight recognition.

Responsibilities: Researched and implemented keyframe recognition algorithms, and used YOLOn11pose to address livestock body keypoint recognition challenges.

Achievements: Data annotation platform delivered for enterprise acceptance in 2025.12, with the algorithms still iterating. Enriched practical experience in computer vision.

Projects

Introduction: ZhituCareer+ is a career-planning web platform built around multi-agent decision making. AIFrameQuest is a community platform built with Flask and Vue, supporting user authentication, content management and image search with Faiss vector search and BERT feature extraction. Two spin-off projects came out of it, ReminisceneStone (a memory-recording and resonance platform built entirely on user-generated content) and MoonPit (a professional image management and search platform with a self-built image database). Tech stack: Python, Flask, JavaScript, MySQL and Vue.

Responsibilities: Wrote the front-end and back-end code for the core deep learning module, integrated the sub-modules, contributed to front-end design and concept design, and allocated work across the team.

Achievements: First place in the course. Open-source output: AIFrameQuest, ZhituCareer+.

Selected Open-Source Work

• MatchaFlow — multi-agent software development team. GitHub
• DLFaceDetection — RPC / remote function call sample. GitHub
• WeSpeak — open-source output of the news communication and large models research. GitHub
• Reptile — open-source output of the news communication and large models research. GitHub
• RecRedTeam — red-team audit framework for LLM and agentic recommender systems. GitHub
• Crusaders — human–machine collaboration framework. GitHub
• Open Stethoscope — heart sound AI murmur detection for grassroots healthcare. GitHub
• OnChainGov — on-chain DAO governance research toolchain with causal inference. GitHub