I am Zhenyu Hou, a PhD student in the Department of Computer Science and Technology at Tsinghua University. I am a member of KEG and am advised by Prof. Yuxiao Dong and Prof. Jie Tang.

My current research interests are Language Model Agent and Reasoning; Reinforcement Learning; LLM Alignment; Self-Supervised Learning.

Project experiences

• Led post-training efforts for GLM models, with a focus on reasoning quality, alignment, and robust real-world behavior.
• Project lead of the GLM-4.5 series models, driving agentic capability design, evaluation, and iteration.

Education

• PhD student, Department of Computer Science and Technology, Tsinghua University (September 2021 - present)
• Bachelor’s degree, Department of Computer Science and Technology, Tsinghua University (September 2017 - July 2021)

Selected publications

Most-cited first-author papers on Google Scholar:

1. GraphMAE: Self-Supervised Masked Graph Autoencoders (ICML 2022, first author; most cited paper in KDD 2022) [GitHub]
2. GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner (WWW 2023, first author) [GitHub]
3. GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models (arXiv 2025)
4. T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling (ICML 2025)
5. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools (arXiv 2024)
6. Self-Supervised Attributed Graph Learning: A Comprehensive Review (TKDE 2021)

Profiles

• Google Scholar: https://scholar.google.com/citations?hl=zh-CN&oi=ao&user=44W9SfwAAAAJ
• GitHub: https://github.com/think2try
• KEG: https://keg.cs.tsinghua.edu.cn/