Published in IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021
A review of self-supervised learning methods on attributed graphs.
Recommended citation: Xie, Y., Xu, Z., Ji, J., Wang, Z., Wang, S., Liu, J., Ding, T., Hou, Z., and Tang, J. (2021). "Self-Supervised Attributed Graph Learning: A Comprehensive Review." IEEE TKDE.
Download Paper
Published in IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021
AutoProNE automatically searches for optimal graph filters to enhance any graph representations.
Recommended citation: Hou, Z., Cen, Y., Dong, Y., Zhang, J., and Tang, J. (2021). "Automated Unsupervised Graph Representation Learning." IEEE TKDE.
Download Paper
Published in ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022
KDD 2022 paper proposing masked autoencoding for self-supervised graph representation learning.
Recommended citation: Hou, Z., Liu, X., Cen, Y., Dong, Y., Yang, H., Wang, C., and Tang, J. (2022). "GraphMAE: Self-Supervised Masked Graph Autoencoders." KDD.
Download Paper
Published in AAAI Conference on Artificial Intelligence (AAAI), 2023
A multi-task framework reformulating symptom checking as multi-label classification for automatic diagnosis.
Recommended citation: Hou, Z., Cen, Y., Liu, Z., Wu, D., Wang, B., Li, X., Hong, L., and Tang, J. (2023). "MTDiag: An Effective Multi-Task Framework for Automatic Diagnosis." AAAI.
Download Paper
Published in ACM Web Conference (WWW), 2023
A unified and efficient library for graph deep learning research and applications.
Recommended citation: Cen, Y., Hou, Z., Wang, Y., Chen, Q., Luo, Y., Yu, Z., et al. (2023). "CogDL: A Comprehensive Library for Graph Deep Learning." WWW.
Download Paper
Published in ACM Web Conference (WWW), 2023
WWW 2023 paper extending masked graph autoencoding with enhanced decoding for stronger self-supervised graph representation learning.
Recommended citation: Hou, Z., et al. (2023). "GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner." WWW.
Download Paper
Published in AAAI Conference on Artificial Intelligence (AAAI), 2024
Using LLMs and hypergraph learning for hyperedge prediction tasks.
Recommended citation: Hou, Z., Fang, Y., Liu, Z., Cen, Y., Zheng, V., and Tang, J. (2024). "Harnessing Large Language Models for Hyperedge Prediction." AAAI.
Download Paper
Published in arXiv, 2024
An RLHF pipeline for ChatGLM with strategies for stable large-scale training and alignment.
Recommended citation: Hou, Z., Niu, Y., Du, Z., Zhang, X., Liu, X., Zeng, A., Zheng, Q., Huang, M., Wang, H., Tang, J., and Dong, Y. (2024). "ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback." arXiv:2404.00934.
Download Paper
Published in arXiv, 2024
A technical report of the ChatGLM model family from GLM-130B to GLM-4.
Recommended citation: Zeng, A., Liu, X., Du, Z., Wang, Z., Lai, H., Hou, Z., and others. (2024). "ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools." arXiv:2406.12793.
Download Paper
Published in International Conference on Learning Representations (ICLR), 2025
A systematic study of RLHF scaling properties across data, model size, and inference budget.
Recommended citation: Hou, Z., Du, P., Niu, Y., Du, Z., Zeng, A., Liu, X., Huang, M., Wang, H., Tang, J., and Dong, Y. (2025). "Does RLHF Scale? Exploring the Impacts From Data, Model, and Method." ICLR.
Download Paper
Published in International Conference on Machine Learning (ICML), 2025
T1 studies reasoning improvements via reinforcement learning and inference-time scaling.
Recommended citation: Hu, W., Xu, C., Hou, Z., et al. (2025). "T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling." ICML.
Download Paper
Published in arXiv, 2025
GLM-4.5 introduces ARC-oriented large language models for agentic behavior, reasoning, and coding.
Recommended citation: Zhipu AI et al. (2025). "GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models." arXiv:2508.06471.
Download Paper
Published in arXiv, 2026
A technical report for GLM-5, focused on agentic engineering, long-horizon reasoning, and coding.
Recommended citation: GLM-5 Team, Zeng, A., Lv, X., Hou, Z., Du, Z., Zheng, Q., Chen, B., Yin, D., Ge, C., et al. (2026). "GLM-5: from Vibe Coding to Agentic Engineering." arXiv:2602.15763.
Download Paper