Jie Ren (任洁)

I am a fifth-year Ph.D. candidate under the supervision of Prof. Quanshi Zhang in Shanghai Jiao Tong University. I received my B.Eng. degree from Shanghai Jiao Tong University in 2020.

My research mainly focuses on trustworthy AI, including the interpretability and safety in LLMs, CV, and machine learning. Now, I am in a group for explainable AI.

🔥I am actively seeking for full-time machine learning/LLM reseacher opportunities starting in 2025. Please feel free to contact me if interested!

Email  /  Google Scholar  /  Github

profile photo
Publications
Identifying Semantic Induction Heads to Understand In-Context Learning   [arXiv]
Jie Ren, Qipeng Guo, Hang Yan, Dongrui Liu, Quanshi Zhang, Xipeng Qiu, and Dahua Lin
ACL findings, 2024
Interpretability of Neural Networks Based on Game-Theoretic Interactions  
Huilin Zhou, Jie Ren, Huiqi Deng, Xu Cheng, Jinpeng Zhang, and Quanshi Zhang
MIR, 2024
Defining and Quantifying the Emergence of Sparse Concepts in DNNs   [arXiv]   [code]
Jie Ren*, Mingjie Li*, Qirui Chen, Huiqi Deng, and Quanshi Zhang
CVPR, 2023
Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?   [arXiv]   [code]
Jie Ren, Zhanpeng Zhou, Qirui Chen, Quanshi Zhang
ICLR, 2023
Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs   [arXiv]   [code]
Jie Ren*, Mingjie Li*, Meng Zhou, Shih-Han Chan, Quanshi Zhang
ICML, 2022
A Unified Game-Theoretic Interpretation of Adversarial Robustness   [arXiv]   [code]
Jie Ren*, Die Zhang*, Yisen Wang*, Lu Chen, Zhanpeng Zhou, Yiting Chen, Xu Cheng, Xin Wang, Meng Zhou, Jie Shi, and Quanshi Zhang
NeurIPS, 2021
Interpreting and Disentangling Feature Components of Various Complexity from DNNs   [arXiv]   [code]
Jie Ren*, Mingjie Li*, Zexu Liu, Quanshi Zhang
ICML, 2021
A Unified Approach to Interpreting and Boosting Adversarial Transferability   [arXiv]   [code]
Xin Wang*, Jie Ren*, Shuyun Lin, Xiangming Zhu, Yisen Wang, Quanshi Zhang
ICLR, 2021
Mining Interpretable AOG Representations from Convolutional Networks via Active Question Answering
Quanshi Zhang, Jie Ren, Ge Huang, Ruiming Cao, Ying Nian Wu, Song-Chun Zhu
IEEE T-PAMI, 2020
Attributes Obfuscation with Complex-Valued Features
Liyao Xiang, Hao Zhang, Haotian Ma, Yifan Zhang, Jie Ren, Quanshi Zhang
ICLR, 2020
Explaining Neural Networks Semantically and Quantitatively
Runjin Chen, Hao Chen, Jie Ren, Ge Huang, Quanshi Zhang
ICCV, 2019 (oral)
Internship
  • [2023.11 - 2024.04]   Shanghai AI Lab · OpenLMLab · pre-train group of InternLM
       Investigate the representation of semantic relationships in attention heads of LLMs.
       Discover the close relationship between the learning of semantic relationships and the emergence of In-Context Learning throughout the pre-training process of LLMs.
Professional Services
Awards
  • [2022.12]   Member of Wen-Tsün Wu Honorable Class of SJTU (Ph.D.)
  • [2022.11]   Huatai Securities Technology Scholarship
  • [2022.07]   ICML 2022 Outstanding Reviewers (Top 10%)
  • [2022.06]   Prize for Outstanding Student Contribution, Huawei Technology Co. Ltd
  • [2020.02]   Second Prize for Outstanding Ph.D. Student, John Hopcroft Center, Shanghai Jiao Tong University
  • [2017, 2018, 2019]   Scholarship for Outstanding Undergraduate Students, Shanghai Jiao Tong University
Invited Talks
  • [2021.10]   Give an online talk at AI安全与隐私论坛.
  • [2021.07]   Give an invited talk at AI drive.
  • [2021.04]   Give an online talk to NAIE, Huawei technologies Inc.
Teaching Assistants
  • [Spring 2021]   Maching Learning (CS385 for undergraduates), SJTU
  • [Fall 2020]   Discrete Mathematics (MA238 for undergraduates), SJTU

Thanks Jon Barron for this template.