I am Zhitian Hou(侯智天), a second-year Master’s student in Computer Technology at SYSU, advised by Prof. Kun Zeng. I am currently an intern at Infix.ai, under the supervision of Prof. Hongxia Yang. Prior to this, I received my Bachelor’s degree in 2023 from SCNU, where I studied in the TAM Lab under the supervision of Prof. Tianyong Hao. My current research interests lie primarily in Natural Language Processing (NLP), Large Language Models (LLMs), and Medical MLLMs, with previous research experience in Legal AI.
🔥 News
- 2025.09: 🎉🎉 Our paper “Large Language Models Meet Legal Artificial Intelligence: A Survey” has been published on arXiv.
- 2025.07: 🎉🎉 Our paper “QCSH: Quantization Controlled Semantic Hashing for Effective Similar Text Search” has been accepted to IEEE SMC Conference 2025.
- 2025.05: 🎉🎉 Our paper “Infi-Med: Low-Resource Medical MLLMs with Robust Reasoning Evaluation” has been published on arXiv.
- 2025.04: 🎉🎉 Our paper “KnowJudge: A Knowledge-Driven Framework for Legal Judgment Prediction” has been accepted to CogSci 2025.
- 2022.10: 🎉🎉 Our paper “Homogeneous ensemble models for predicting infection levels and mortality of COVID-19 patients: Evidence from China” has been accepted to Digital Health.
📝 Publications
Large Language Models Meet Legal Artificial Intelligence: A Survey
Zhitian Hou, Zihan Ye, Nanli Zeng, Tianyong Hao, Kun Zeng
- This paper provides a comprehensive review of 16 legal LLMs series and 47 LLM-based frameworks for legal tasks, and also gather 15 benchmarks and 29 datasets to evaluate different legal capabilities. Additionally, we analyse the challenges and discuss future directions for LLMbased approaches in the legal domain. We hope this paper provides a systematic introduction for beginners and encourages future research in this field.
QCSH: Quantization Controlled Semantic Hashing for Effective Similar Text Search
Zihan Ye, Zhitian Hou, Ge Lin, Kun Zeng
- We propose an unsupervised novel semantic text hashing framework, Quantization Controlled Semantic Hashing (QCSH), which enhances feature representation while refines the binarization process.
Infi-Med: Low-Resource Medical MLLMs with Robust Reasoning Evaluation
Zeyu Liu$^*$, Zhitian Hou$^*$, Yining Di, Kejing Yang, Zhijie Sang, Congkai Xie, Jingwen Yang, Siyuan Liu, Jialu Wang, Chunming Li, Ming Li, Hongxia Yang
- We propose Infi-Med, a comprehensive framework for medical MLLMs that introduces three key innovations: (1) a resource-efficient approach through curating and constructing high-quality supervised fine-tuning (SFT) datasets with minimal sample requirements, with a forward-looking design that extends to both pretraining and posttraining phases; (2) enhanced multimodal reasoning capabilities for cross-modal integration and clinical task understanding; and (3) a systematic evaluation system that assesses model performance across medical modalities and task types.
Homogeneous ensemble models for predicting infection levels and mortality of COVID-19 patients: Evidence from China
Jiafeng Wang$^*$, Xianlong Zhou$^*$, Zhitian Hou$^*$, Xiaoya Xu, Yueyue Zhao, Shanshan Chen, Jun Zhang, Lina Shao, Rong Yan, Mingshan Wang, Minghua Ge, Tianyong Hao, Yuexing Tu, and Haijun Huang
- We proposed two homogeneous ensemble models based on clinical features of COVID-19 patients for predicting infection levels and mortality.
🎖 Honors and Awards
- 2024.09 First-Grade Scholarship, SYSU
- 2023.06 Outstanding Graduate, SCNU
- 2023.06 37 Interactive Entertainment Scholarship, 37 Interactive Entertainment
- 2023.04 First-Grade Scholarship, SCNU
- 2022.10 “Intelligent Base” Future Star Scholarship，Ministry of Education & Huawei
- 2021.04 First-Grade Scholarship, SCNU
- 2021.04 Finalist (F Award), Mathematical Contest in Modeling (MCM), COMAP
📖 Educations
- 2023.09 - present, Master, Computer Technology, School of Computer Science and Engineering, Sun Yat-sen University.
- 2019.09 - 2023.06, Undergraduate, Artificial Intelligence, School of Computer Science, South China Normal University.