About me
Hi there, I’m Yizhuo Lv 👋
I am currently pursuing my Master’s degree at Qilu University of Technology (QLU), under the supervision of Prof. Chong Di. Concurrently, I serve as a Research Assistant in the Medical and AI Team at the Shandong Artificial Intelligence Institute (SDAI) (2025–2027). Driven by a passion for structuring, reasoning, and decision-making in complex systems, my research lies at the intersection of Graph Learning, Reinforcement Learning, and Large Language Models. My core research interests include:
- Dynamic Graph Learning & Spatiotemporal Data Mining: We build scalable Temporal Graph Neural Networks (TGNNs) to model non-Euclidean topological evolutions, aiming to capture intricate spatiotemporal dependencies and solve complex sequential decision problems like Dynamic Influence Maximization (DIM) over non-stationary networks.
- Reinforcement Learning under Dynamic Constraints: We design sample-efficient Deep Reinforcement Learning (DRL) and Hierarchical Reinforcement Learning (HRL) frameworks tailored for non-stationary environments, addressing exploration-exploitation trade-offs to enhance the decision-making adaptability of autonomous systems.
- Large Language Models & Multimodal Intelligence: We focus on the training, alignment, and parameter-efficient finetuning (PEFT) of LLMs and Multimodal Large Language Models (MLLMs), optimizing their downstream adaptability and cross-modal cognitive capabilities for complex task execution.
- Autonomous Agents & Hybrid Retrieval-Augmented Generation (RAG): We engineer cutting-edge AI Agent systems and hybrid RAG frameworks, emphasizing tool-orchestration, multi-agent collaboration, and structured knowledge-graph integration to build highly reliable, factually grounded applications.
🔥 News
2026.07: 🧬 Successfully completed Phase II of the Crop Breeding Agent Platform (Breeding) at the Peking University Institute of Modern Agriculture!
2026.03: 💼 Joined Netthink Technology Co., Ltd. as an Algorithm Intern.
2026.01: 🎉 The invention patent “A Temporal-Aware Dynamic Influence Maximization Method for Smart Homes” was authorized.
2025.12: 🏆 Won the National Second Prize in the “Huawei Cup” Post-Graduate Mathematical Modeling Contest!
2025.08: 🤝 Participated in the collaborative project “Multidimensional Information Perception and Scene Goal Generation” with Haier Technology.
2025.07: 💼 Joined the Medical and AI Team at SDAI as a Research Assistant.
2024.09: 🎓 Started my M.S. journey at Qilu University of Technology.
📝 Publications
- Chinese Invention Patent: A Time-Aware Dynamic Influence Maximization Method for Smart Homes, Chong Di#, Yizhuo Lv, Minglei Shu, Zhaoyang Liu, Zhen Cui, Yunlong Tian, Yukai Zhu (# corresponding author) (Patent No. ZL202511475850.5, Authorized, Jan. 2026) [Link]
🤝 Projects
AI Policy Consultation & Agent Service Platform
- Autonomous ReAct Agent: Designed a full-stack agent with intent-driven tool orchestration and dynamic context management, reducing invalid tool calls by 40%.
- Hybrid RAG & Session Memory: Built a multi-source hybrid RAG pipeline with semantic chunking (+25% accuracy) and integrated a Redis-backed multi-level cache.
Crop Breeding Agent Platform (Breeding)
- Domain LLM & Agent Framework: Developed and deployed a specialized agricultural agent platform to accelerate genomic selection, trait prediction, and collaborative crop breeding pipelines.
- Multi-Source Integration & Tool-Use: Integrated multi-source phenotypic, genomic, and environmental data with advanced tool-use capabilities to empower molecular breeders with reliable, factually grounded decision support.
🏆 Awards & Honors
2025: National Second Prize, 22nd HUAWEI Cup China Postgraduate Mathematical Modeling Contest
2024: First Prize, 15th National College Students Mathematics Competition (Non-Mathematics Category A)
2024: Outstanding Graduate, Xinyang University (XYU)
2022: First Prize (Provincial Level), China Undergraduate Mathematical Contest in Modeling (CUMCM), Henan Division
2022: Third Prize, 15th SPSSPRO Cup Mathematical Modeling Competition of China Math Union
2025: Third Prize Academic Scholarship (Postgraduate Level), Qilu University of Technology (QLU)
2024: Third Prize Academic Scholarship (Postgraduate Level), Qilu University of Technology (QLU)
2023: Third Prize Academic Scholarship (Undergraduate Level), Xinyang University (XYU)
2022: Second Prize Academic Scholarship (Undergraduate Level), Xinyang University (XYU)
2021: First Prize Academic Scholarship (Undergraduate Level), Xinyang University (XYU)
📖 Educations
2024.09 – Present, Pursuing M.S. in Artificial Intelligence, Qilu University of Technology (QLU), Jinan
2020.09 – 2024.06, B.S. in Computer Science and Technology, Xinyang University (XYU), Xinyang, Henan
💻 Internships
2026.03 – 2026.07: Algorithm Intern, Netthink Technology Co., Ltd. (Focus: Large Language Model (LLM) Agents, Hybrid RAG, and Multimodal LLMs)
2025.07 – 2026.03: Research Assistant, Medical and AI Team, Shandong Artificial Intelligence Institute (SDAI) (Focus: Data Mining, Reinforcement Learning, and Spatiotemporal Deep Learning)