CoolFace
Apppublic

zhanchao019/test_server_wacv

sourceHugging Faceupdated 8mo agoView on Hugging Face
1likes
App README

TopoCoT @ WACV 2026

The 1st WACV 2026 Workshop on Robust and Generalized Lane Topology Understanding and HD Map Generation through CoT Design (TopoCoT) seeks to provide a platform for industry experts and academics to brainstorm and exchange ideas about road understanding CoT and its derived outstanding works to advance autonomous driving. Through a half-day in-person event, the workshop will showcase regular and demo paper presentations and invited talks from famous researchers in academia and industry. Additionally, TopoCoT will launch two open-source real-world CoT lane topology reasoning datasets. The workshop will host a challenge based on this dataset to assess the capabilities of language and computer vision models in addressing HD map generation challenges.

Important Dates/Links

  • —Datasets: Challenge
  • —Workshop Day: Mar 6 or Mar 7, 2026
  • —Accepted papers will be published in the WACV 2026 proceedings.

Submission Guidelines and Review Process

  • —Authors are encouraged to submit high-quality, original technical reports.
  • —All submissions should follow the same template as for the main WACV2026 conference. Please refer to the WACV Author Kit.

Topics

The workshop will cover a wide range of topics, including but not limited to:

  • —LLM for lane topology understanding and HD map generation.
  • —VLM for lane topology understanding and HD map generation.
  • —CoT for lane topology understanding and HD map generation.
  • —Reinforcement learning for lane topology understanding and HD map generation.
  • —Transfer learning for lane topology understanding and HD map generation.
  • —World modeling and simulation for lane topology understanding and HD map generation.
  • —Evaluation metrics and benchmarks for lane topology understanding and HD map generation.

Organizers

<table> <tr> <td width="150"><img src="https://topocotwacv26.github.io/img/zhenli.png" width="120"></td> <td><strong><a href="https://mypage.cuhk.edu.cn/academics/lizhen/">Dr. Zhen Li</a></strong><br>Assistant Professor, CUHKSZ</td> </tr> <tr> <td><img src="https://scholar.googleusercontent.com/citations?viewop=mediumphoto&user=6A1yEFMAAAAJ&citpid=1" width="120"></td> <td><strong><a href="https://scholar.google.com/citations?user=6A1yEFMAAAAJ&hl=zh-CN&oi=ao">Dr. Chao Zheng</a></strong><br>Tencent</td> </tr> <tr> <td><img src="https://lihongyang.info/content/hongyangli.jpg" width="120"></td> <td><strong><a href="https://lihongyang.info/">Dr. Hongyang Li</a></strong><br>Assistant Professor, HKU</td> </tr> <tr> <td><img src="https://air.tsinghua.edu.cn/_local/A/E0/B9/8151B5539B8747D4663584D7A212F9F80B8_4C0F.jpg" width="120"></td> <td><strong><a href="https://sites.google.com/view/fromandto/">Dr. Hao Zhao</a></strong><br>Assistant Professor, THU</td> </tr> </table>

Program Committee

<table> <tr> <td width="150"><img src="https://topocotwacv26.github.io/img/yimingyang.jpg" width="120"></td> <td><strong><a href="https://yimingyang23.github.io/">Yiming Yang</a></strong><br>CUHKSZ</td> <td width="150"><img src="https://topocotwacv26.github.io/img/chaozhan.jpg" width="120"></td> <td><strong>Chao Zhan</strong><br>CUHKSZ</td> </tr> <tr> <td><img src="https://topocotwacv26.github.io/img/yaoyihuan.jpg" width="120"></td> <td><strong>Yihuan Yao</strong><br>CUHKSZ</td> <td><img src="https://raw.githubusercontent.com/LLVM-AD/llvm-ad.github.io/main/assets/img/KunTang.jpg" width="120"></td> <td><strong>Kun Tang</strong><br>Tencent</td> </tr> <tr> <td><img src="https://raw.githubusercontent.com/LLVM-AD/llvm-ad.github.io/main/assets/img/ZhipengCao.jpg" width="120"></td> <td><strong>Zhipeng Cao</strong><br>Tencent</td> <td><img src="https://topocotwacv26.github.io/img/erlong.jpg" width="120"></td> <td><strong>Erlong Li</strong><br>Tencent</td> </tr> <tr> <td><img src="https://topocotwacv26.github.io/img/yanchao.jpg" width="120"></td> <td><strong>Chao Yan</strong><br>Tencent</td> <td><img src="https://topocotwacv26.github.io/img/lishiyao.jpg" width="120"></td> <td><strong>Shiyao Li</strong><br>Tencent</td> </tr> <tr> <td><img src="https://scholar.googleusercontent.com/citations?viewop=viewphoto&user=oXWRBrwAAAAJ&citpid=34" width="120"></td> <td><strong><a href="https://scholar.google.com/citations?user=oXWRBrwAAAAJ&hl=zh-CN&oi=sra">Xu Cao</a></strong><br>UIUC</td> <td><img src="https://topocotwacv26.github.io/img/itscheadshots/yifan.jpg" width="120"></td> <td><strong><a href="https://shenyifans.github.io/">Yifan Shen</a></strong><br>UIUC</td> </tr> <tr> <td><img src="https://scholar.googleusercontent.com/citations?viewop=viewphoto&user=notEEFMAAAAJ&citpid=9" width="120"></td> <td><strong><a href="https://ysma.me/">Yunsheng Ma</a></strong><br>Purdue</td> <td><img src="https://topocotwacv26.github.io/img/zhirunyue.jpg" width="120"></td> <td><strong>Zhirun Yue</strong><br>THU</td> </tr> </table>

Schedule

Workshop Date: Mar 6 or Mar 7, 2026

Workshop Location: TBD

Please find the tentative workshop schedule below:

TimeEventSpeaker
13:00 -- 13:10Opening Remarks
13:10 -- 13:40Topic: TBDHongyang Li (HKU)
13:40 -- 14:10Topic: TBDHengshuang Zhao (HKU)
14:10 -- 14:40Technical reportsAuthors
14:40 -- 15:00Coffee Break
15:00 -- 15:30Topic: TBDManmohan Chandraker (UC San Diego)
15:30 -- 16:00Topic: TBDJim Rehg (UIUC)
16:00 -- 16:30Topic: TBDZiran Wang (Purdue)
16:30 -- 17:00Summary of the WorkshopZhen Li (CUHKSZ)
17:00 -- 17:10Closing Remarks

Contact Us

If you have any questions or inquiries, please contact us at email.

Citation

If the workshop inspire you, please consider citing our work:

@article{wang2023openlane,
    title={Openlane-v2: A topology reasoning benchmark for unified 3d hd mapping},
    author={Wang, Huijie and Li, Tianyu and Li, Yang and Chen, Li and Sima, Chonghao and Liu, Zhenbo and Wang, Bangjun and Jia, Peijin and Wang, Yuting and Jiang, Shengyin and others},
    journal={Advances in Neural Information Processing Systems},
    volume={36},
    pages={18873--18884},
    year={2023}
}

@article{li2023lanesegnet,
    title={Lanesegnet: Map learning with lane segment perception for autonomous driving},
    author={Li, Tianyu and Jia, Peijin and Wang, Bangjun and Chen, Li and Jiang, Kun and Yan, Junchi and Li, Hongyang},
    journal={arXiv preprint arXiv:2312.16108},
    year={2023}
}

@article{yang2025topo2seq,
  title={Topo2Seq: Enhanced Topology Reasoning via Topology Sequence Learning},
  author={Yang, Yiming and Luo, Yueru and He, Bingkun and Li, Erlong and Cao, Zhipeng and Zheng, Chao and Mei, Shuqi and Li, Zhen},
  journal={AAAI 2025},
  year={2025}
}

@article{yang2025topostreamer,
  title={TopoStreamer: Temporal Lane Segment Topology Reasoning in Autonomous Driving},
  author={Yang, Yiming and Luo, Yueru and He, Bingkun and Lin, Hongbin and Fu, Suzhong and Zheng, Chao and Cao, Zhipeng and Li, Erlong and Yan, Chao and Cui, Shuguang and others},
  journal={arXiv preprint arXiv:2507.00709},
  year={2025}
}

@article{yang2025fastopowm,
  title={FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World Models},
  author={Yang, Yiming and Lin, Hongbin and Luo, Yueru and Fu, Suzhong and Zheng, Chao and Yan, Xinrui and Mei, Shuqi and Tang, Kun and Cui, Shuguang and Li, Zhen},
  journal={arXiv preprint arXiv:2507.23325},
  year={2025}
}

@article{luo2025reltopo,
  title={RelTopo: Enhancing Relational Modeling for Driving Scene Topology Reasoning},
  author={Luo, Yueru and Zhou, Changqing and Yang, Yiming and Li, Erlong and Zheng, Chao and Mei, Shuqi and Cui, Shuguang and Li, Zhen},
  journal={arXiv preprint arXiv:2506.13553},
  year={2025}
}