Shujie Yang

Hi there👋 thanks for visiting my website! I'm a MS student at the Tsinghua-Berkeley Shenzhen Institute @ Tsinghua University, where I am fortunate to be advised by Prof. Kaichen Dong and co-supervised by Prof. Yansong Tang. I affiliated with the Dong lab and IVG-SZ. Prior to that, I obtained my bachelor's degree in mathematics at Xi'an Jiaotong University (2019-2023) and had wonderful time conducting research at the LUD lab advised by Prof. Minnan Luo.

My research generally focuses on social network, graph neural networks, LLM for Recommendation, Reinforcement Learning and AI for Science (currently)...

In 2023, I spent a spring at VIP Group @ SUSTech to work with Prof. Jinbao Wang.

I was in Xiaohongshu AIGC group as a research intern in the end of 2024 and the beginning of 2025.

I will join Kuaishou Recommendation LLM Group as a research intern in the summer of 2025.

Please feel free to drop me an Email for any form of communication or collaboration!☘️

Email: /

profile photo
🔥 What's New
Research (* indicates equal contribution)

My primary research interest lies at LLMs, AIGC (Text-to-Image Generation etc.) and AI for Science, with a particular focus on AI for photonics and Subject-driven Image/Video Generation.

OneRec-V2
OneRec-V2 Technical Report
Guorui Zhou, ..., Shujie Yang, ..., Ziming Li et al.
arXiv 2025
arXiv PDF

We propose OneRec-V2 with Lazy Decoder-Only Architecture that eliminates encoder bottlenecks and incorporates real-world user feedback for better preference alignment.

OneRec
OneRec Technical Report
Guorui Zhou, Jiaxin Deng, ..., Shujie Yang, ..., Zhanyu Liu et al.
arXiv 2025
Hugging Face PDF

We propose OneRec, which reshapes the recommendation system through an end-to-end generative approach and achieves promising results. Firstly, we have enhanced the computational FLOPs of the current recommendation model by 10 × and have identified the scaling laws for recommendations within certain boundaries.

3DSP
CoSP: Reconfigurable Multi-State Metamaterial Inverse Design via Contrastive Pretrained Large Language Model
Shujie Yang, Xuzhe Zhao, Yuqi Zhang, Yansong Tang, Kaichen Dong
Submitted
3DSP
Cauchyformer: Physics-Informed Few-shot Spectrum Inference for Photonic Metasurfaces
Shujie Yang, Chunjiang Li, Hongyan Fu, Yansong Tang, Kaichen Dong
Submitted
GADY
GADY: Unsupervised Anomaly Detection on Dynamic Graphs
Shiqi Lou, Qingyue Zhang, Shujie Yang, Zhaoxuan Tan, Yuyang Tian, Minnan Luo
arxiv ePrints
AHEAD
AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approach
Shujie Yang, Binchi Zhang, Shangbin Feng, Zhaoxuan Tan, Qinghua Zheng, Jun Zhou, Minnan Luo
Proceedings of 2023 Chinese Intelligent Automation Conference
Github Best Paper

We propose AHEAD: a heterogeneity-aware unsupervised graph anomaly detection approach based on the encoder-decoder framework.

TwiBot-22
TwiBot-22: Towards Graph-Based Twitter Bot Detection
Shangbin Feng*, Zhaoxuan Tan*, Herun Wan*, Ningnan Wang*, Zilong Chen*, Binchi Zhang*, Qinghua Zheng, Wenqian Zhang, Zhenyu Lei, Shujie Yang, Xinshun Feng, Qingyue Zhang, Hongrui Wang, Yuhan Liu, Yuyang Bai, Heng Wang, Zijian Cai, Yanbo Wang, Lijing Zheng, Zihan Ma, Jundong Li, Minnan Luo
Proceedings of NeurIPS, Datasets and Benchmarks Track, 2022
website GitHub bibtex poster

We present TwiBot-22, the largest graph-based Twitter bot detection benchmark to date, which provides diversified entities and relations in Twittersphere and has considerably better annotation quality.

Education
Tsinghua University Tsinghua-Berkeley Shenzhen Institute
2023.08 - present
M.S. in Data Science and Information Technology
Advisor: Prof. Kaichen Dong
Co-supervised by Prof. Yansong Tang
Xi'an Jiaotong University School of Mathematics and Statistics
2019.08 - 2023.07
B.E. in Information and Computational Science
Advisor: Prof. Minnan Luo
Academic Experiences
Recommendation Large Language Model Group @ Kuaishou
Research Intern (Recommendation LLMs)      2025.6 - now
Worked on applying large language models to recommendation scenarios, focusing on RLHF of generative recommendation LLM.
Mentor: Qigen Hu
AIGC Group @ Xiaohongshu AIGC Group
Research Intern      2024.11 - 2025.3
Worked on improving the performance of text2image generation models like Stable Diffusion and Flux.
Mentor: Shuang Sun
VIP Group @ Southern University of Science and Technology
Visiting Student      2023.02 - 2023.5
Worked on anomaly detection on industrial images.
Mentor: Jinbao Wang
Advisor: Prof. Feng Zheng
Luo lab Undergraduate Division (LUD) @ Xi'an Jiaotong University
Member      2022.10 - present
Conducted research on various topics including social network analysis and heterogeneous graph anomaly detection.
Advisor: Prof. Minnan Luo
Miscellaneous