About Me
Hi, I’m now a 1st year PhD student at GaTech. I am working on the interaction of HCI and ML, especially in fragile LLMs and how to fix them. I collaborate with Prof. Xiang Anthony Chen and Sherry Wu. I was a member of Microsoft Research working with Dr. Jiang Bian on LLM Agents. Subscribe to my newsletter for research updates.
I care about promoting open, collaborative, and reproducible research. I do not limit myself to specific techniques but instead always look for better solutions and good problems. I am looking for internship opportunities for summer 2026.
In my spare time, I have keen interests in visualization, communication design, and VI systems. Everything should be able to be expressed or explained in vivid and simple ways. Anime, movies, and music are also my favorites. My goal is to be a great professor for students in places like here. Yes, I love teaching and sharing knowledge.
- Network&Connection
- Data Mining
- HCI
- LLM Agent
Undergraduate in Artificial Intelligence, 21.09 - 25.06
South China University of Technology
PhD Student in Machine Learning, 25.08 - 29.05
Georgia Institute of Technology
News
- 2025.09. One paper about LLM very unaligned privacy issues in physical world is released in Paper, Codes and Data. As we move from chatbot to embodied agents, LLMs are still fragile in privacy protection, especially with increasingly complex environments. Check it out!
- 2025.06. I just release a new blog about the LLM’s tendency to directly answer questions or assume wrong conditions, facing incomplete questions with missing information. Check it out here.
- 2025.03. We now release the model and code of our SIGIR 2025 paper. Series models has been receiving 1.9M+ monthly downloads on HuggingFace. Codes and Weights.
- 2025.02. Our paper about Inference-free sparse retrievers has been accepted by SIGIR 2025. Check it out in here. Free from over-sparsification and welcome the superior performance of SPLADE models with 1/5 FLOPS. Thanks for Inference-free style.
- I will fill some details during this time, including new internship and paper at Amazon and SIGIR. Forgive my laziness~
- 2024.08. Check our new open-source project for evolving agents in Research and development (R&D) here; Online demo is available here. More news from Microsoft Research will be expected!!!
All News
- 2024.07. I win the “Star of Tomorrow” award from Microsoft Research Asia, which is the highest honor for excellent internship.
- 2024.06. I am invited to the summer workshop of CUHK business school. More discussion from different perspectives will be expected, especially in the field of recommendation system and data mining.
- 2024.06. We release the dataset of Idea Reviewing for LLM agents. Check the details here and in projects section.
- 2024.06. I was invited to visit Soochow University, Nanjing University of Science and Technology, and Tongji University for discussion about the development and future of intellectual property.
- 2024.06. I was invited to the Fifth China Intellectual Property Innovation and Development Forum to give a speech, check the gallery for more details. Thank the great welcome from Prof. Jianwei Dang and etc.
- 2024.05. One paper abut multiview clustering by Grassmann manifold is accepted by TNNLS. Check the early access version here.
- 2024.04. Great pleasure to bridge and help Tec-Do become official advertising agency of Microsoft! Check the news here.
- 2024.03. Check our new paper about efficient WSI fusion on arXiv here!
- 2024.03. One paper about autonomous Data-Centric R&D LLM agents accepted by ICLR 2024 AGI Workshop! Check it out in here.
- 2024.03. One paper about accepted by WWW 2024 short! Simple multigraph convolution networks that is efficient and effective for cross-view interaction among multigraph. Check the details in here
- 2024.01. One paper is accepted by WWW 2024, 4/4 positive reviews! See you in Signapore! Check the details in here.
- 2024.01. The DSP platform we built are awarded as the Product of the Year in Tec-Do. Congrats to our team!
- 2023.12. I join the Graph Mind Research Group at Dartmouth College with Prof. Yujun Yan. It will be a great journey to explore the expressive and generalizable power of graph neural networks.
- 2023.12. One patent is granted. See the details here.
- 2023.10. We are excited to submit two papers to TKDE 2024 and one paper to WWW 2024. Fingers crossed!
- 2023.10. We are excited to release the preprint of our paper “NP2L: Negative Pseudo Partial Labels Extraction for Graph Neural Networks”. Check it out in arXiv.
- 2023.09. I am honored to be invited to give a talk about basic knowledge of graph neural networks and their applications in Relation Study Workshop. Check the slides in here.
- 2023.08. We are excited to announce the next generation of manga reader, Byreader, is released. Check it out in the projects section and github.
- 2023.08 I am honored that the diffusion based real-person model picture generation product is exhibited in 31st Guangzhou Expo at the China Import and Export Fair Complex and reported by CCTV. Check the news in here.
- 2023.07. I am honored to further bridge the cooperation between the Tec-Do and SCUT. A cooperation agreement for laboratory construction and talent training was signed between the two parties. Check the news in here.
- 2023.04. I join the Multi-relational Geometric Information Interaction Research Group at Xi’an Jiaotong University with Prof. Danyang Wu. Research on the graph neural network, geometric representation learning and their applications for RNA, protein, and brain networks.
- 2022.12. I am honored to be awarded the TaiHu Innovation Prize (1%), the highest scholarship awarded by the Wuxi governments.
- 2022.09. I join the Tec-Do as a Data Mining and Machine Learning Engineer. Core new product will be developed soon, stay tuned!
- 2022.09. I am honored to be awarded the National Scholarship (1%), the highest scholarship awarded by the Chinese governments.
- 2022.09. I am honored to be awarded the First Price (1%) Scholarship, the highest scholarship awarded by the South China University of Technology.
- 2022.06. I lead our team to win the Second Prize (8%) in the Intel Cup Undergraduate Electronic Design Contest by the project of Multimodal Fitness Intelligent Guidance System. See the details in the project section. Thanks to the guidance of Prof. Lin Shu.
- 2021.12. I lead our team to win the First Prize (1%) in the Baidu Paddle Paddle Cup.
Projects
Experience
Working with Prof. Anthony Chen from UCLA and Prof. Sherry Wu from CMU. Investigate the over-reliance issues on LLM by designed large-scale user study, with quantization, statistics methods, customized webs and browser extension.
One paper submitted to CSCW 2025.
Working with Dr. Jian Bian, Microsoft Research Asia. Research on Automatic Research and Development (R&D) and Quantitative Finance Strategy. Imagine a world where the R&D process is fully automated, and the LLM can automatic generate analysis results of every proposed ideas and propose new ideas. Project we led is open-sourced in: Github/RD-Agent. I also won the highest honor “Star of Tomorrow” awarded by MSRA.
One paper accepted by ICLR 2024 AGI Workshop.
Advised by Prof. Danyang Wu. Research on the graph neural network, geometric representation learning and their applications for RNA, protein, and brain networks.
Two paper accepted by WWW 2024, two papers pending.
Responsibilities for CTR/CVR prediction and Smart Bidding. Project of the Year awarded. Achievements include:
- Build CTR (Click-through rate) predication model though GBDT and GNN for the Tec-Do Ads DSP platform, defeating 3rd party (Cusper) SaaS services. Achieved ROI 1.4x from 0.7x.
- Use DQN Implemented smart bidding module under constraint budget. 30% ROI improvement.
- Apply negative pseudo partial labels to sampling negative samples for recall model on item-user bipartite graph. To know more about negative pseudo partial labels, check our paper here.
- Build workflow generating realistic picture for e-commerce based on diffusion model. One tweet shows the example here. Check more selected news in here, here and here.
- Two patent granted, two patents published, and two patents pending.
Featured Publications
Recent & Upcoming Talks
Acknowledgements
I have been fortunate to work with many talented and dedicated individuals who have generously shared their time and expertise with me. I am grateful for their support and encouragement.
- Qinyi Zhou, Chang Liu @Tsinghua University
- Yuxuan Ren, Haoyu Chi @USTC
- Prof. Xiang ‘Anthony’ Chen @UCLA
- Prof. Sherry Wu @CMU
- Prof. Danyang Wu @Xi’an Jiaotong University
- Prof. Yujun Yan @Dartmouth College
- Prof. Jin Xu, Lin Shu, Shidang Xu, Yahui Jia @South China University of Technology
- Dr. Guanyong Lu, Dr. Pinde Chen, Guofeng Huang, Shuhao Li @Tec-Do
- Xiao Yang, Xu Yang, Weiqing Liu, Jiang Bian @Microsoft
- Prof. Dawei Zhou @Virginia Tech
- Zeqi Ye @NanKai University
I also thanks friends in anime club, who always bring me joy and mental support.
Gallery
Enjoy both research and life
Contact
Reach me by email if you have any questions.
- xinjie@gatech.edu
- 777 Xingye Avenue East, Guangzhou, 511442
- Book an appointment