I am Zhitian Hou(侯智天), a third-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 “InfiMed-Foundation: Pioneering Advanced Multimodal Medical Models with Compute-Efficient Pre-Training and Multi-Stage Fine-Tuning” has been published on arXiv.
  • 2025.09:  🎉 Our paper “InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning” has been published on arXiv.
  • 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.
  • 2025.04:  🎉 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

🩺 Medical MLLM

Arxiv 2025
sym

InfiMed-Foundation: Pioneering Advanced Multimodal Medical Models with Compute-Efficient Pre-Training and Multi-Stage Fine-Tuning

Guanghao Zhu, Zhitian Hou, Zeyu Liu, Zhijie Sang, Congkai Xie, Hongxia Yang

**HF**

  • Multimodal large language models (MLLMs) have shown remarkable potential in various domains, yet their application in the medical field is hindered by several challenges. General-purpose MLLMs often lack the specialized knowledge required for medical tasks, leading to uncertain or hallucinatory responses …
Arxiv 2025
sym

InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning

Zeyu Liu$^*$, Zhitian Hou$^*$, Guanghao Zhu, Zhijie Sang, Congkai Xie, Hongxia Yang

**HF** **HF**

  • In this work, we introduce the InfiMed-Series models, including InfiMed-SFT-3B and InfiMed-RL-3B, a set of multimodal large language models (MLLMs) specialized for medical tasks.
Arxiv 2025
sym

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.
CogSci 2025
sym

KnowJudge: A Knowledge-Driven Framework for Legal Judgment Prediction

Zhitian Hou, Jinlin Li, Ge Lin, Kun Zeng

  • We proposed KnowJudge, a knowledge-driven cognitive simulation framework and introduces the Law Keyword Recognition (LKR) dataset.

Others

🎖 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.

💻 Internships

  • 2025.06 - present, Research Intern, Infix.ai, Shenzhen.
  • 2022.09 - 2023.06, Research Intern, TAM Lab, Guangzhou.