Biography

Currently, I am working at the Shanghai AI Lab as a Research Fellow. I got a Ph.D. degree from Shanghai Jiao Tong University and was supervised by Prof. Quanshi Zhang. Before that, I received my B.Sc. degree from Northeastern University.

My research interests include topics in the trustworthiness of multi-modal foundation models. We are looking for full-time employees, interns, and joint PhDs (with SJTU/FDU, etc) to work together on foundation models’ safety/robustness/explainability. Please drop me an email liudongrui@pjlab.org.cn if you are interested.

Selected Awards

  • CVPR 2024 Best Paper Candidates
  • Outstanding Graduate Student, Shanghai Jiao Tong University
  • Longhu Scholarship
  • National Scholarship
  • Wireless Scholarship

Academic Services

Reviewer: ICML, CVPR, ICCV, ECCV, NeurIPS, ICLR, AISTATS, ICRA, PAMI, IJCV, TKDE, TVCG, TCSVT

Publications

  • DEAN: Deactivating the Coupled Neurons to Mitigate Fairness-Privacy Conflicts in Large Language Models [pdf]
    Chen Qian, Dongrui Liu, Jie Zhang, Yong Liu, Jing Shao

  • REEF: Representation Encoding Fingerprints for Large Language Models [pdf]
    Jie Zhang, Dongrui Liu, Chen Qian, Linfeng Zhang, Yong Liu, Yu Qiao, Jing Shao

  • Decouple-Then-Merge: Towards Better Training for Diffusion Models [pdf]
    Qianli Ma, Xuefei Ning, Dongrui Liu, Li Niu, Linfeng Zhang

  • Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues [pdf]
    Qibing Ren, Hao Li, Dongrui Liu, Zhanxu Xie, Xiaoya Lu, Yu Qiao, Lei Sha, Junchi Yan, Lizhuang Ma, Jing Shao

  • Towards the Dynamics of a DNN Learning Symbolic Interactions [pdf]
    Qihan Ren, Yang Xu, Junpeng Zhang, Yue Xin, Dongrui Liu, Quanshi Zhang
    accepted by 37th Conference on Neural Information Processing Systems (NeurIPS 2024)

  • The Better Angels of Machine Personality: How Personality Relates to LLM Safety [pdf]
    Jie Zhang, Dongrui Liu, Chen Qian, Ziyue Gan, Yu Qiao, Yong Liu, and Jing Shao
    Arxiv

  • Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models [pdf]
    Chen Qian, Jie Zhang, Wei Yao, Dongrui Liu, Zhenfei Yin, Yu Qiao, Yong Liu, and Jing Shao
    accepted by ACL 2024

  • Identifying Semantic Induction Heads to Understand In-Context Learning [pdf]
    Jie Ren, Qipeng Guo, Hang Yan, Dongrui Liu, Xipeng Qiu, and Dahua Lin
    accepted by ACL 2024

  • Self-Supervised Multi-Frame Neural Scene Flow [pdf]
    Dongrui Liu, Daqi Liu, Xueqian Li, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, and Lei Chu
    on Arxiv

  • MLP Can Be A Good Transformer Learner [pdf]
    Sihao Lin, Pumeng Lyu, Dongrui Liu, Tao Tang, Xiaodan Liang, Andy Song, and Xiaojun Chang
    accepted by CVPR 2024 (Best Paper Award Candidates)

  • Explaining Generalization Power of a DNN using Interactive Concepts [pdf]
    Huilin Zhou, Hao Zhang, Huiqi Deng, Dongrui Liu, Wen Shen, Shih-Han Chan, and Quanshi Zhang
    accepted by AAAI 2024

  • Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities [pdf]
    Dongrui Liu, Huiqi Deng, Xu Cheng, Qihan Ren, Kangrui Wang, and Quanshi Zhang
    accepted by 37th Conference on Neural Information Processing Systems (NeurIPS 2023)

  • Self-Supervised Point Cloud Registration with Deep Versatile Descriptors for Intelligent Driving [pdf]
    Dongrui Liu, Chuanchuan Chen, Changqing Xu, Robert Qiu, and Lei Chu
    accepted by IEEE Transactions on Intelligent Transportation Systems (T-ITS)

  • SAKS: Sampling Adaptive Kernels from Subspace for Point Cloud Graph Convolution [pdf]
    Chuanchuan Chen, Dongrui Liu, Changqing Xu, and Trieu-Kien Truong
    accepted by IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

  • PFMixer: Point Cloud Frequency Mixing [pdf]
    Dongrui Liu, Shiyun Liu, Chuanchuan Chen, Zhengyun Jiang, and Changqing Xu
    accepted by IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022)

  • PointFP: A Feature-Preserving Point Cloud Sampling [pdf]
    Dongrui Liu, Chuanchuan Chen, Shiyun Liu, Zhengyun Jiang, and Changqing Xu
    accepted by IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022)

  • Point Clouds Downsampling Based on Complementary Attention and Contrastive Learning [pdf]
    Chuanchuan Chen, Dongrui Liu, and Changqing Xu
    accepted by IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022)

  • A Robust and Reliable Point Cloud Recognition Network Under Rigid Transformation [pdf]
    Dongrui Liu, Chuanchuan Chen, Changqing Xu, Qi Cai, Lei Chu, Fei Wen, and Robert Qiu
    accepted by IEEE Transactions on Instrumentation and Measurement (TIM)

  • Trap of Feature Diversity in the Learning of MLPs [pdf]
    Dongrui Liu, Shaobo Wang, Jie Ren, Kangrui Wang, Sheng Yin, Huiqi Deng, and Quanshi Zhang
    arxiv

  • Point Cloud Registration using Representative Overlapping Points [pdf]
    Lifa Zhu, Dongrui Liu, Changwei Lin, Rui Yan, Francisco Gómez-Fernández, Ninghua Yang, and Ziyong Feng
    arxiv

  • GeneCGAN: A conditional generative adversarial network based on genetic tree for point cloud reconstruction [pdf]
    Chuanchuan Chen, Dongrui Liu, Changqing Xu, and Trieu-Kien Truong
    accepted by Neurocomputing

  • Interpreting Representation Quality of DNNs for 3D Point Cloud Processing [pdf]
    Wen Shen, Qihan Ren, Dongrui Liu, Quanshi Zhang
    accepted by 35th Conference on Neural Information Processing Systems (NeurIPS 2021)