Jiaming Liu
Liu Jiaming (刘家铭)
Bachelor degree (2015-2019)
北京邮电大学 Beijing University of Posts and Telecommunications
伦敦大学玛丽女王学院Queen Mary University of London
Master graduate (2019-2022)
北京邮电大学 Beijing University of Posts and Telecommunications
Pattern Recognition and Intelligent Systems Lab (PRIS Lab)
Employee (2022-2023)
OPPO研究院 OPPO Research Institute
Supervised by OPPO Chief Scientist - Yandong Guo
P.h.D candidate (2023-Now)
北京大学 Peking University, School of Computer Science
National Key Laboratory for Multimedia Information Processing
Email: liujiaming@bupt.cn, jiamingliu@stu.pku.edu.cn

About Me (Google Scholar)

Supervisor

I am currently a P.h.D student at National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, China, supervised by Prof. Shanghang Zhang .
We have several academic visitor and intern positions at HMI Lab (Peking University). We actively work on Out Of Distribution Generalization, Automatic Driving Perception, Multi-Modal Learning, and 3D Vision. If you like what we do, don't hesitate to contact me.

Research Interests

    My past research mainly focuses on Autonomous Driving, Out Of Distribution, and Neural Video Delivery. My current research direction is Continual learning, Embodied AI, and 3D vision.

News

  • 2024: Two papers were accepted by ECCV2024 (Multimodal Large Language Models + 3D large-scale model).
  • 2024: Six papers were accepted by CVPR2024 (Continual learning + Multimodal Large Language Models + Robotic Manipulation).
  • 2024: Four papers were accepted by ICRA2024 (BEV 3D detection + 3D Occupancy prediction + Continual learning + Spike camera).
  • 2024: One paper was accepted by ICLR2024 (Parameter efficient fine-tuning + Continual learning).
  • 2024: Three papers were accepted by AAAI2024 (BEV 3D detection + MOE + Continual learning).
  • 2023: We achieved two champions in the ICCV2023 Challenge - Multitask Learning & Continual Test-time Adaptation.
  • 2023: We (UniOCC) achieved 3rd place in the CVPR2023 Challenge - Vision-Centric 3D Occupancy Prediction.
  • 2023: Three papers were accepted by MICCAI2023, ICASSP2023, and NOSSDAV2023.
  • 2023: Three papers were accepted by CVPR2023 (BEV 3D detection + Continual Learning + Quantization).

Publications (First author or Project leader)

Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding
Yiwen Tang, Jiaming Liu (equal contribution), Dong Wang, Zhigang Wang, Shanghang Zhang, Bin Zhao, Xuelong Li

European Conference on Computer Vision (ECCV), 2024

[PDF]  [Code] 

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
Jiaming Liu, Ran Xu, Senqiao Yang, Renrui Zhang, Qizhe Zhang, Zehui Chen, Yandong Guo, Shanghang Zhang

Computer Vision and Pattern Recognition (CVPR), 2024

[PDF]  [Web page] 

Cloud-Device Collaborative Learning for Multimodal Large Language Models
Guanqun Wang, Jiaming Liu (equal contribution), Chenxuan Li, Yuan Zhang, Junpeng Ma, Xinyu Wei, Kevin Zhang, Maurice Chong, Renrui Zhang, Yijiang Liu, Shanghang Zhang

Computer Vision and Pattern Recognition (CVPR), 2024

[PDF] 

Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer
Jiaming Liu, Qizhe Zhang, Xiaoqi Li Jianing Li, Ming Lu, Tiejun Huang, Shanghang Zhang

International Conference on Robotics and Automation ICRA, 2024

[PDF]  [Code] 

Multi-latent Space Alignments for Unsupervised Domain Adaptation in Multi-view 3D Object Detection
Jiaming Liu, Rongyu Zhang, Xiaowei Chi, Xiaoqi Li, Ming Lu, Yandong Guo, Shanghang Zhang

International Conference on Robotics and Automation ICRA, 2024

[PDF]  [Code] 

Renderocc: Vision-centric 3d occupancy prediction with 2d rendering supervision
Mingjie Pan, Jiaming Liu (equal contribution), Renrui Zhang, Peixiang Huang, Xiaoqi Li, Li Liu, Shanghang Zhang

International Conference on Robotics and Automation ICRA, 2024

[PDF]  [Code] 

Distribution-Aware Continual Test Time Adaptation for Semantic Segmentation
Jiayi Ni, Senqiao Yang, Jiaming Liu (project leader), Xiaoqi Li, Wenyu Jiao, Ran Xu, Zehui Chen, Yi Liu, Shanghang Zhang

International Conference on Robotics and Automation ICRA, 2024

[PDF] 

ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
Jiaming Liu, Senqiao Yang, Peidong Jia, Ming Lu, Yandong Guo, Wei Xue, Shanghang Zhang

International Conference on Learning Representations ICLR, 2024

[PDF]  [Code] 

Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction
Senqiao Yang, Jiarui Wu, Jiaming Liu (project leader), Xiaoqi Li, Qizhe Zhang, Mingjie Pan, Shanghang Zhang

Thirty-Eighth AAAI Conference on Artificial Intelligence AAAI, 2024

[PDF]  [Code] 

RepCaM: Re-parameterization Content-aware Modulation for Neural Video Delivery
Rongyu Zhang, Lixuan Du, Jiaming Liu (project leader), Xiaoqi Li, Ming Lu, Yandong Guo, Shanghang Zhang

Network and Operating System Support for Digital Audio and Video (NOSSDAV), CCF B

[PDF] 

BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks
Xiaowei Chi, Jiaming Liu (equal contribution), Ming Lu, Rongyu Zhang, Zhaoqing Wang, Yandong Guo, Shanghang Zhang

Computer Vision and Pattern Recognition (CVPR), 2023

[PDF] 

Adaptive Patch Exiting for Scalable Single Image Super-Resolution
Shizun Wang, Jiaming Liu (equal contribution), Kaixin Chen, Xiaoqi Li, Ming Lu, Yandong Guo

European Conference on Computer Vision (ECCV Oral), 2022

[PDF]  [Code] 

Efficient Meta-Tuning for Content-aware Neural Video Delivery
Xiaoqi Li, Jiaming Liu (equal contribution), Shizun Wang, Cheng Lyu, Ming Lu, Yurong Chen, Anbang Yao, Yandong Guo, Shanghang Zhang

European Conference on Computer Vision (ECCV), 2022

[PDF]  [Code] 

Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
Jiaming Liu, Ming Lu, Kaixin Chen, Xiaoqi Li, Shizun Wang, Zhaoqing Wang, Enhua Wu, Yurong Chen, Chuang Zhang, Ming Wu

International Conference on Computer Vision (ICCV), 2021

[PDF]  [Code] 

Publications (Coauthor)

LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model
Yulin Luo, Ruichuan An, Bocheng Zou, Yiming Tang, Jiaming Liu, Shanghang Zhang

European Conference on Computer Vision (ECCV), 2024

[PDF] 

Manipllm: Embodied multimodal large language model for object-centric robotic manipulation
Xiaoqi Li, Mingxu Zhang, Yiran Geng, Haoran Geng, Yuxing Long, Yan Shen, Renrui Zhang, Jiaming Liu, Hao Dong

Computer Vision and Pattern Recognition (CVPR), 2024

[PDF]  [Web page] 

No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation
Xiangyang Zhu, Renrui Zhang, Bowei He, Ziyu Guo, Jiaming Liu, Han Xiao, Chaoyou Fu, Hao Dong, Peng Gao

Computer Vision and Pattern Recognition (CVPR Spotlight), 2024

[PDF] 

FreeKD: Knowledge Distillation via Semantic Frequency Prompt
Yuan Zhang, Tao Huang, Jiaming Liu, Tao Jiang, Kuan Cheng, Shanghang Zhang

Computer Vision and Pattern Recognition (CVPR), 2024

[PDF] 

NTO3D: Neural Target Object 3D Reconstruction with Segment Anything
Xiaobao Wei, Renrui Zhang, Jiarui Wu, Jiaming Liu, Ming Lu, Yandong Guo, Shanghang Zhang

Computer Vision and Pattern Recognition (CVPR), 2024

[PDF] 

Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation
Rongyu Zhang, Yulin Luo, Jiaming Liu, Huanrui Yang, Zhen Dong, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Yuan Du, Shanghang Zhang

Thirty-Eighth AAAI Conference on Artificial Intelligence AAAI, 2024

[PDF] 

Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-Supervised 3D Object Detection
Hongzhi Gao, Zheng Chen, Zehui Chen, Lin Chen, Jiaming Liu, Shanghang Zhang, Feng Zhao

Thirty-Eighth AAAI Conference on Artificial Intelligence AAAI, 2024

[PDF] 

DiffuseIR:Diffusion Models For Isotropic Reconstruction of 3D Microscopic Images
Mingjie Pan, Yulu Gan, Jiaming Liu, Aimin Wang, Shanghang Zhang, Dawei Li

Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2023, CCF B

[PDF] 

CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network With Large Input
Senmao Tian, Ming Lu, Jiaming Liu, Yandong Guo, Yurong Chen, Shunli Zhang

Computer Vision and Pattern Recognition (CVPR), 2023

[PDF] 

Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-World
Yulu Gan, Mingjie Pan, Rongyu Zhang, Zijian Ling, Jiaming Liu, Shanghang Zhang

Computer Vision and Pattern Recognition (CVPR), 2023

[PDF] 

MTTrans: Cross-Domain Object Detection with Mean Teacher Transformer
Jinze Yu, Jiaming Liu, Xiaobao Wei, Haoyi Zhou, Yohei Nakata, Denis Gudovskiy, Tomoyuki Okuno, Jianxin Li, Kurt Keutzer, Shanghang Zhang

European Conference on Computer Vision (ECCV), 2022

[PDF] 

SamplingAug: On the Importance of Patch Sampling Augmentation for Single Image Super-Resolution
Shizun Wang, Ming Lu, Kaixin Chen, Jiaming Liu, Xiaoqi Li, Ming Wu

The British Machine Vision Conference (BMVC), 2021

[PDF]  [Code] 

Awards

1st Workshop on Visual Continual Learning, @ICCV 2023
Jiaming Liu (Peking University), Ran Xu, Senqiao Yang, Peidong, Jia, Jiayi Ni

Champion of ICCV 2023 Challenge - Continual Test-time Adaptation for Semantic Segmentation

[Challenge Web] 

1st Workshop on Visual Continual Learning, @ICCV 2023
Zehui Chen (USTC), Jiaming Liu (Peking University)

Champion of ICCV 2023 Challenge - Multitask Learning for Robustness

[Challenge Web] 

UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering
Mingjie Pan (Xiaomi Car), Jiaming Liu (Peking University)

3rd place of CVPR 2023 Challenge - Vision-Centric 3D Occupancy Prediction

[Technical Report]  [Challenge Web] 

Last Updated on 21th February, 2024