I am currently co-leading the base model group for GLM. I received a PhD in the Department of Computer Science and Technology at Tsinghua University in 2025, advised by Prof. Jie Tang.
My research interest lies in various aspects of pretrained language models, especially how to improve their general intelligence[ACL'21,ACL'21,NeurIPS'24,ICLR'25]. Generally, I am also interested in the application of machine learning algorithms to real-world systems, including information retrieval [ECML/PKDD'18,TKDE,SIGIR'19], recommender systems[KDD'19] and knowledge graphs [TKDE].
In my spare time, I like to read science fiction novels and history books.
PhD in Computer Science, 2020 - Now
Tsinghua University
B.E. in Computer Science, 2016 - 2020
Tsinghua University
[28/07/25] We release GLM-4.5, the SoTA open-source language model for intelligent agents.
[23/01/25] Our paper Scaling Speech-Text Pre-training with Synthetic Interleaved Data is accepted at ICLR 2025.
[25/10/24] We release GLM-4-Voice, an end-to-end speech chat model that supports both English and Chinese.
[26/09/24] Our paper Understanding Emergent Abilities of Language Models from the Loss Perspective is accepted at NeurIPS 2024.
[05/06/24] We release GLM-4-9B, with superior performance beyond Llama-3-8B and long context length up to 128K context.