🎓 About Me
I am currently an Associate Professor in the School of Computer and Communication Engineering, University of Science and Technology Beijing. My research interests focus on 3D generative AI and Embodied AI, including motion capture & synthesis, 3D reconstruction, 3D scene generation, computer graphics, image/video generation and robotics. Before I joined USTB, I obtained my B.E. and Ph.D. degrees from Tsinghua University, and Institute of Automation，Chinese Academy of Sciences, under the supervision of Prof. Tieniu Tan and Prof. Zhaoxiang Zhang. After that I joined Huawei and deeply cooperate with Lingxi Xie under the supervision of Prof. Qi Tian. After that I have founded a startup Cheery.AI for a while. Now I’m in deep cooperation with Prof. Zhaoxiang Zhang in Institute of Automation，Chinese Academy of Sciences and Prof. Xucheng Yin in USTB.
🔈 Join Us
If you are interested in our projects on 3D vision, generative AI, or embodied AI, please feel free to contact me for potential collaboration or exchange. You can reach out via email or WeChat.
随时欢迎对三维视觉、生成式人工智能、具身智能、LLM感兴趣的老师/研究生/本科生/实习生通过jrpeng4ever@126.com联系合作、交流
🔥 News
- 2024.10: One paper accepted by NeurIPS 2024 D&B.
- 2024.08: One paper accepted by ACL 2024 Findings.
- 2024.07: Two papers accepted by ACM MM 2024 as oral representations.
- 2024.07: One paper accepted by ECCV 2024.
- 2024.07: One paper accepted by TPAMI 2024.
- 2024.02: One paper accepted by CVPR 2024.
📝 Selected Publications
RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
Jiaheng Liu, Zehao Ni, Haoran Que, Tao Sun, Zekun Wang, Jian Yang, Jiakai Wang, Hongcheng Guo, Zhongyuan Peng, Ge Zhang, Jiayi Tian, Xingyuan Bu, Ke Xu, Wenge Rong, Junran Peng, Zhaoxiang Zhang
NeurIPS Dataset and Benchmark Track 2024
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models [Paper] [Code]
Zekun Moore Wang*, Zhongyuan Peng*, Haoran Que*, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Stephen W. Huang, Jie Fu, Junran Peng
Findings of the Association for Computational Linguistics (Findings of ACL) 2024
LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling [Paper]
JiahengLiu\∗, JianhaoLi\∗, KaisiyuanWang, HongchengGuo, JianYang1, Junran Peng, KeXu, XianglongLiu, JinyangGuo1†
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024
Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels [Paper]
CongPan\∗, JunranPeng\∗, XingyuanBu, ZhaoxiangZhang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2023
Logformer: A pre-train and tuning pipeline for log anomaly detection [Paper]
Hongcheng Guo, Jian Yang, Jiaheng Liu, Jiaqi Bai, Boyang Wang, Zhoujun Li, Tieqiao Zheng, Bo Zhang, Junran Peng, Qi Tian
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2024
BAEFormer: Bi-Directional and Early Interaction Transformers for Bird’s Eye View Semantic Segmentation [Paper]
Cong Pan, Yonghao He, Junran Peng, Qian Zhang, Wei Sui, Zhaoxiang Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023
DATA: Domain-aware and task-aware self-supervised learning [Paper]
Qing Chang, Junran Peng, Lingxie Xie, Jiajun Sun, Haoran Yin, Qi Tian, Zhaoxiang Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023
Delving into the effectiveness of receptive fields: Learning scale-transferrable architectures for practical object detection [Paper]
Zhaoxiang Zhang, Cong Pan, Junran Peng
International Journal of Computer Vision (IJCV) 2022
Uncertainty-aware pseudo label refinery for domain adaptive semantic segmentation [Paper]
Yuxi Wang, Junran Peng, ZhaoXiang Zhang
IEEE/CVF International Conference on Computer Vision (ICCV) 2021
Gaia: A transfer learning system of object detection that fits your needs [Paper]
Xingyuan Bu, Junran Peng, Junjie Yan, Tieniu Tan, Zhaoxiang Zhang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021
Large-scale object detection in the wild from imbalanced multi-labels [Paper]
Junran Peng, Xingyuan Bu, Ming Sun, Zhaoxiang Zhang, Tieniu Tan, Junjie Yan
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020
Efficient neural architecture transformation search in channel-level for object detection [Paper]
Junran Peng, Ming Sun, Zhaoxiang Zhang, Tieniu Tan, Junjie Yan
Neural Information Processing Systems (NeurIPS) 2019
POD: Practical object detection with scale-sensitive network [Paper]
Junran Peng, Ming Sun, Zhaoxiang Zhang, Tieniu Tan, Junjie Yan
IEEE/CVF International Conference on Computer Vision (ICCV) 2019
📄 Pre-Prints
Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering [Paper]
Chang Yu, Junran Peng, Xiangyu Zhu, Zhaoxiang Zhang, Qi Tian, Zhen Lei
FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes pre-print [Paper]
Genghao Zhang, Yuxi Wang, Chuanchen Luo, Shibiao Xu, Zhaoxiang Zhang, Man Zhang, Junran Peng
📖 Experiences
-
Associate Professor in the School of Computer and Communication Engineering, University of Science and Technology Beijing
Date: 2024.09 ~ (now) -
CEO of Cheery.AI Date: 2023.07 ~ 2024.07
-
Lead Engineer in the Team PanGu, Huawei Cloud.
Date: 2021.01 ~ 2023.07
Leader: Prof. Qi Tian. -
Ph.D in the Institute of Automation, Chinese Academy of Sciences
Date: 2015.09 ~ 2020.07
Supervisor: Prof. Tieniu Tan and Prof. Zhaoxiang Zhang (张兆翔). -
B.E. in the Department of Computer Science and Technology, Tsinghua University Date: 2011.09 ~ 2015.07