publications | Jiachen Lu

2025

GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals

Jiachen Lu, Hailan Shanbhag, and Haitham Al Hassanieh

In Conference on Neural Information Processing Systems (NeurIPS), 2025

Spotlight Presentation

@inproceedings{lu2025geraf,
  title = {GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals},
  author = {Lu, Jiachen and Shanbhag, Hailan and Al Hassanieh, Haitham},
  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
  year = {2025},
}

Translating Images to Road Network: A Sequence-to-Sequence Perspective

Jiachen Lu, Ming Nie, Bozhou Zhang, Renyuan Peng, Xinyue Cai, Hang Xu, Feng Wen, Wei Zhang, and Li Zhang

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

DOI arXiv Bib HTML Code

@article{lu2025translating,
  title = {Translating Images to Road Network: A Sequence-to-Sequence Perspective},
  author = {Lu, Jiachen and Nie, Ming and Zhang, Bozhou and Peng, Renyuan and Cai, Xinyue and Xu, Hang and Wen, Feng and Zhang, Wei and Zhang, Li},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2025},
  publisher = {IEEE},
  doi = {10.1109/TPAMI.2025.3612940},
}

SeaFormer++: Squeeze-enhanced axial transformer for mobile visual recognition

Qiang Wan, Zilong Huang, Jiachen Lu, Gang Yu, and Li Zhang

International Journal of Computer Vision (IJCV), 2025

DOI arXiv Bib HTML Code

@article{wan2025seaformer++,
  title = {SeaFormer++: Squeeze-enhanced axial transformer for mobile visual recognition},
  author = {Wan, Qiang and Huang, Zilong and Lu, Jiachen and Yu, Gang and Zhang, Li},
  journal = {International Journal of Computer Vision (IJCV)},
  volume = {133},
  number = {6},
  pages = {3645--3666},
  year = {2025},
  publisher = {Springer},
  doi = {10.1007/s11263-025-02345-2},
}

S-nerf++: Autonomous driving simulation via neural reconstruction and generation

Yurui Chen, Junge Zhang, Ziyang Xie, Wenye Li, Feihu Zhang, Jiachen Lu, and Li Zhang

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025

DOI arXiv Bib HTML Code

@article{chen2025s,
  title = {S-nerf++: Autonomous driving simulation via neural reconstruction and generation},
  author = {Chen, Yurui and Zhang, Junge and Xie, Ziyang and Li, Wenye and Zhang, Feihu and Lu, Jiachen and Zhang, Li},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2025},
  publisher = {IEEE},
  doi = {10.1109/TPAMI.2025.3543072},
}

2024

Vision transformers: From semantic segmentation to dense prediction

Li Zhang, Jiachen Lu, Sixiao Zheng, Xinxuan Zhao, Xiatian Zhu, Yanwei Fu, Tao Xiang, Jianfeng Feng, and Philip HS Torr

International Journal of Computer Vision (IJCV), 2024

DOI arXiv Bib HTML Code

@article{zhang2024vision,
  title = {Vision transformers: From semantic segmentation to dense prediction},
  author = {Zhang, Li and Lu, Jiachen and Zheng, Sixiao and Zhao, Xinxuan and Zhu, Xiatian and Fu, Yanwei and Xiang, Tao and Feng, Jianfeng and Torr, Philip HS},
  journal = {International Journal of Computer Vision (IJCV)},
  volume = {132},
  number = {12},
  pages = {6142--6162},
  year = {2024},
  publisher = {Springer},
  doi = {10.1007/s11263-024-02173-w}
}

Wovogen: World volume-aware diffusion for controllable multi-camera driving scene generation

Jiachen Lu, Ze Huang, Zeyu Yang, Jiahui Zhang, and Li Zhang

In European Conference on Computer Vision (ECCV), 2024

arXiv Bib HTML PDF Code Poster

@inproceedings{lu2024wovogen,
  title = {Wovogen: World volume-aware diffusion for controllable multi-camera driving scene generation},
  author = {Lu, Jiachen and Huang, Ze and Yang, Zeyu and Zhang, Jiahui and Zhang, Li},
  booktitle = {European Conference on Computer Vision (ECCV)},
  pages = {329--345},
  year = {2024},
  organization = {Springer},
}

Lanegraph2seq: Lane topology extraction with language model via vertex-edge encoding and connectivity enhancement

Renyuan Peng, Xinyue Cai, Hang Xu, Jiachen Lu, Feng Wen, Wei Zhang, and Li Zhang

In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024

arXiv Bib HTML PDF Code

@inproceedings{peng2024lanegraph2seq,
  title = {Lanegraph2seq: Lane topology extraction with language model via vertex-edge encoding and connectivity enhancement},
  author = {Peng, Renyuan and Cai, Xinyue and Xu, Hang and Lu, Jiachen and Wen, Feng and Zhang, Wei and Zhang, Li},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
  volume = {38},
  number = {5},
  pages = {4497--4505},
  year = {2024},
}

Softmax-free linear transformers

Jiachen Lu, Junge Zhang, Xiatian Zhu, Jianfeng Feng, Tao Xiang, and Li Zhang

International Journal of Computer Vision (IJCV), 2024

DOI arXiv Bib HTML Code

@article{lu2024softmax,
  title = {Softmax-free linear transformers},
  author = {Lu, Jiachen and Zhang, Junge and Zhu, Xiatian and Feng, Jianfeng and Xiang, Tao and Zhang, Li},
  journal = {International Journal of Computer Vision (IJCV)},
  volume = {132},
  number = {8},
  pages = {3355--3374},
  year = {2024},
  publisher = {Springer},
  doi = {10.1007/s11263-024-02035-5}
}

Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping

Zijie Pan, Jiachen Lu, Xiatian Zhu, and Li Zhang

In The Twelfth International Conference on Learning Representations (ICLR), 2024

arXiv Bib HTML Code

@inproceedings{pan2023enhancing,
  author = {Pan, Zijie and Lu, Jiachen and Zhu, Xiatian and Zhang, Li},
  title = {Enhancing High-Resolution 3D Generation through Pixel-wise Gradient
                    Clipping},
  booktitle = {The Twelfth International Conference on Learning Representations (ICLR)},
  year = {2024},
}

2023

Translating images to road network: A non-autoregressive sequence-to-sequence approach

Jiachen Lu, Renyuan Peng, Xinyue Cai, Hang Xu, Hongyang Li, Feng Wen, Wei Zhang, and Li Zhang

In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023

Oral arXiv Bib HTML PDF Code Poster

Oral Presentation

@inproceedings{lu2023translating,
  selected = true,
  title = {Translating images to road network: A non-autoregressive sequence-to-sequence approach},
  author = {Lu, Jiachen and Peng, Renyuan and Cai, Xinyue and Xu, Hang and Li, Hongyang and Wen, Feng and Zhang, Wei and Zhang, Li},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  pages = {23--33},
  year = {2023},
}

Suit: Learning significance-guided information for 3d temporal detection

Zheyuan Zhou, Jiachen Lu, Yihan Zeng, Hang Xu, and Li Zhang

In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023

Oral arXiv Bib HTML

Oral Presentation

@inproceedings{zhou2023suit,
  title = {Suit: Learning significance-guided information for 3d temporal detection},
  author = {Zhou, Zheyuan and Lu, Jiachen and Zeng, Yihan and Xu, Hang and Zhang, Li},
  booktitle = {2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages = {9399--9406},
  year = {2023},
  organization = {IEEE},
}

Generative semantic segmentation

Jiaqi Chen, Jiachen Lu, Xiatian Zhu, and Li Zhang

In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2023

arXiv Bib HTML PDF Code

@inproceedings{chen2023generative,
  title = {Generative semantic segmentation},
  author = {Chen, Jiaqi and Lu, Jiachen and Zhu, Xiatian and Zhang, Li},
  booktitle = {Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR)},
  pages = {7111--7120},
  year = {2023},
}

Seaformer: Squeeze-enhanced axial transformer for mobile semantic segmentation

Qiang Wan, Zilong Huang, Jiachen Lu, Gang Yu, and Li Zhang

In The eleventh international conference on learning representations (ICLR), 2023

arXiv Bib HTML PDF Code

@inproceedings{wan2023seaformer,
  title = {Seaformer: Squeeze-enhanced axial transformer for mobile semantic segmentation},
  author = {Wan, Qiang and Huang, Zilong and Lu, Jiachen and Yu, Gang and Zhang, Li},
  booktitle = {The eleventh international conference on learning representations (ICLR)},
  year = {2023},
}

2022

Learning ego 3d representation as ray tracing

Jiachen Lu, Zheyuan Zhou, Xiatian Zhu, Hang Xu, and Li Zhang

In European conference on computer vision (ECCV), 2022

arXiv Bib HTML PDF Code Poster

@inproceedings{lu2022learning,
  selected = true,
  title = {Learning ego 3d representation as ray tracing},
  author = {Lu, Jiachen and Zhou, Zheyuan and Zhu, Xiatian and Xu, Hang and Zhang, Li},
  booktitle = {European conference on computer vision (ECCV)},
  pages = {129--144},
  year = {2022},
  organization = {Springer},
}

2021

Soft: Softmax-free transformer with linear complexity

Jiachen Lu, Jinghan Yao, Junge Zhang, Xiatian Zhu, Hang Xu, Weiguo Gao, Chunjing Xu, Tao Xiang, and Li Zhang

In Conference on Neural Information Processing Systems (NeurIPS), 2021

Spotlight arXiv Bib HTML PDF Code

Spotlight Presentation

@inproceedings{lu2021soft,
  selected = true,
  title = {Soft: Softmax-free transformer with linear complexity},
  author = {Lu, Jiachen and Yao, Jinghan and Zhang, Junge and Zhu, Xiatian and Xu, Hang and Gao, Weiguo and Xu, Chunjing and Xiang, Tao and Zhang, Li},
  booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
  year = {2021},
}

Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers

Sixiao Zheng, Jiachen Lu, Hengshuang Zhao, Xiatian Zhu, Zekun Luo, Yabiao Wang, Yanwei Fu, Jianfeng Feng, Tao Xiang, Philip HS Torr, and others

In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2021

arXiv Bib HTML PDF Code

@inproceedings{zheng2021rethinking,
  selected = true,
  title = {Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers},
  author = {Zheng, Sixiao and Lu, Jiachen and Zhao, Hengshuang and Zhu, Xiatian and Luo, Zekun and Wang, Yabiao and Fu, Yanwei and Feng, Jianfeng and Xiang, Tao and Torr, Philip HS and others},
  booktitle = {Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR)},
  pages = {6881--6890},
  year = {2021},
}