publications

2026

1. Report

   Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

   Bytedance Seed

   Model Card, 2026

   Bib

   @article{seed18,
     title = {Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity},
     author = {Seed, Bytedance},
     journal = {Model Card},
     year = {2026},
   }

   

2. ICLR

   Unveiling downstream performance scaling of llms: A clustering-based perspective

   Chengyin Xu, Kaiyuan Chen, Xiao Li, Ke Shen, and Chenggang Li

   International Conference on Learning Representations (ICLR), 2026

   Bib arXiv

   @article{xu2025unveiling,
     title = {Unveiling downstream performance scaling of llms: A clustering-based perspective},
     author = {Xu, Chengyin and Chen, Kaiyuan and Li, Xiao and Shen, Ke and Li, Chenggang},
     journal = {International Conference on Learning Representations (ICLR)},
     year = {2026},
   }

   

2025

1. Report

   Seed1.8 Model Card: Towards Generalized Real-World Agency

   Bytedance Seed

   Model Card, 2025

   Bib

   @article{seed19,
     title = {Seed1.8 Model Card: Towards Generalized Real-World Agency},
     author = {Seed, Bytedance},
     journal = {Model Card},
     year = {2025},
   }

   

2. Report

   Seed1.5-VL Technical Report

   Bytedance Seed

   arXiv preprint arXiv:2505.07062, 2025

   Bib arXiv

   @article{seed2025vl,
     title = {Seed1.5-VL Technical Report},
     author = {Seed, Bytedance},
     journal = {arXiv preprint arXiv:2505.07062},
     year = {2025},
   }

   

3. Report

   Seed-thinking-v1.5: Advancing superb reasoning models with reinforcement learning

   Bytedance Seed

   arXiv preprint arXiv:2504.13914, 2025

   Bib arXiv

   @article{seed2025thinking,
     title = {Seed-thinking-v1.5: Advancing superb reasoning models with reinforcement learning},
     author = {Seed, Bytedance},
     journal = {arXiv preprint arXiv:2504.13914},
     year = {2025},
   }

   

4. Report

   Technical Introduction to the Seed1.6 Model Series

   Bytedance Seed

   Technical Report, 2025

   Bib

   @article{seed2025technical,
     title = {Technical Introduction to the Seed1.6 Model Series},
     author = {Seed, Bytedance},
     journal = {Technical Report},
     year = {2025},
     link = {https://seed.bytedance.com/en/seed1_6},
   }

   

5. ICCV

   PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detection

   Xiao Li, Y Zhu, Y Huang, W Zhang, Y He, J Shi, and X Hu

   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025

   Bib arXiv

   @inproceedings{li2025pbcat,
     title = {PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detection},
     author = {Li, Xiao and Zhu, Y and Huang, Y and Zhang, W and He, Y and Shi, J and Hu, X},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
     year = {2025},
   }

   

6. TIFS

   On the Importance of Backbone to the Adversarial Robustness of Object Detectors

   Xiao Li, Hang Chen, and Xiaolin Hu

   IEEE Transactions on Information Forensics and Security (TIFS), 2025

   Bib arXiv

   @article{li2025importance,
     title = {On the Importance of Backbone to the Adversarial Robustness of Object Detectors},
     author = {Li, Xiao and Chen, Hang and Hu, Xiaolin},
     journal = {IEEE Transactions on Information Forensics and Security (TIFS)},
     year = {2025}
   }

   

7. ICLR

   ADBM: Adversarial diffusion bridge model for reliable adversarial purification

   Xiao Li, Wenxuan Sun, Huanran Chen, Qiongxiu Li, Yining Liu, Yingzhe He, Jie Shi, and Xiaolin Hu

   International Conference on Learning Representations (ICLR), 2025

   Bib arXiv Code

   @article{li2024adbm,
     link = {https://openreview.net/forum?id=g0rnZeBguq},
     title = {ADBM: Adversarial diffusion bridge model for reliable adversarial purification},
     author = {Li, Xiao and Sun, Wenxuan and Chen, Huanran and Li, Qiongxiu and Liu, Yining and He, Yingzhe and Shi, Jie and Hu, Xiaolin},
     journal = {International Conference on Learning Representations (ICLR)},
     year = {2025}
   }

   

2024

1. arXiv

   HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks

   Fengji Zhang, Linquan Wu, Huiyu Bai, Guancheng Lin, Xiao Li, Xiao Yu, Yue Wang, Bei Chen, and Jacky Keung

   arXiv preprint arXiv:2410.12381, 2024

   Bib arXiv

   @article{zhang2024humaneval,
     title = {HumanEval-V: Benchmarking High-Level Visual Reasoning with Complex Diagrams in Coding Tasks},
     author = {Zhang, Fengji and Wu, Linquan and Bai, Huiyu and Lin, Guancheng and Li, Xiao and Yu, Xiao and Wang, Yue and Chen, Bei and Keung, Jacky},
     journal = {arXiv preprint arXiv:2410.12381},
     year = {2024},
   }

   

2. arXiv

   Perfect gradient inversion in federated learning: A new paradigm from the hidden subset sum problem

   Qiongxiu Li, Lixia Luo, Agnese Gini, Changlong Ji, Zhanhao Hu, Xiao Li, Chengfang Fang, Jie Shi, and Xiaolin Hu

   arXiv preprint arXiv:2409.14260, 2024

   Bib arXiv

   @article{li2024perfect,
     title = {Perfect gradient inversion in federated learning: A new paradigm from the hidden subset sum problem},
     author = {Li, Qiongxiu and Luo, Lixia and Gini, Agnese and Ji, Changlong and Hu, Zhanhao and Li, Xiao and Fang, Chengfang and Shi, Jie and Hu, Xiaolin},
     journal = {arXiv preprint arXiv:2409.14260},
     year = {2024},
   }

   

3. arXiv

   Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models

   Xiao Li, Zhuhong Li, Qiongxiu Li, Bingze Lee, Jinghao Cui, and Xiaolin Hu

   arXiv preprint arXiv:2410.15362, 2024

   Bib arXiv

   @article{fastergcg,
     title = {Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models},
     author = {Li, Xiao and Li, Zhuhong and Li, Qiongxiu and Lee, Bingze and Cui, Jinghao and Hu, Xiaolin},
     journal = {arXiv preprint arXiv:2410.15362},
     year = {2024}
   }

   

4. ECCV

   PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition

   Xiao Li, Yining Liu, Na Dong, Sitian Qin, and Xiaolin Hu

   European Conference on Computer Vision (ECCV), 2024

   Bib arXiv Code

   @article{lipartimagenetpp,
     title = {PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition},
     author = {Li, Xiao and Liu, Yining and Dong, Na and Qin, Sitian and Hu, Xiaolin},
     journal = {European Conference on Computer Vision (ECCV)},
     year = {2024},
     publisher = {Springer}
   }

   

5. CVPR

   Language-Driven Anchors for Zero-Shot Adversarial Robustness

   Xiao Li, Wei Zhang, Yining Liu, Zhanhao Hu, Bo Zhang, and Xiaolin Hu

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

   Bib arXiv Code

   @inproceedings{li2023languagedriven,
     author = {Li, Xiao and Zhang, Wei and Liu, Yining and Hu, Zhanhao and Zhang, Bo and Hu, Xiaolin},
     title = {Language-Driven Anchors for Zero-Shot Adversarial Robustness},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {24686--24695},
     year = {2024}
   }

   

6. TIFS

   On the Privacy Effect of Data Enhancement via the Lens of Memorization

   Xiao Li, Qiongxiu Li, Zhanhao Hu, and Xiaolin Hu

   IEEE Transactions on Information Forensics and Security (TIFS), 2024

   Bib arXiv Code

   @article{li2024privacy,
     title = {On the Privacy Effect of Data Enhancement via the Lens of Memorization},
     author = {Li, Xiao and Li, Qiongxiu and Hu, Zhanhao and Hu, Xiaolin},
     journal = {{IEEE} Transactions on Information Forensics and Security (TIFS)},
     year = {2024}
   }

   

7. Neuroc..

   Hiding from thermal imaging pedestrian detectors in the physical world

   Xiaopei Zhu, Xiao Li, Jianmin Li, Zheyao Wang, and Xiaolin Hu

   Neurocomputing, 2024

   Bib

   @article{zhu2024hiding,
     link = {https://www.sciencedirect.com/science/article/abs/pii/S0925231223010469},
     title = {Hiding from thermal imaging pedestrian detectors in the physical world},
     author = {Zhu, Xiaopei and Li, Xiao and Li, Jianmin and Wang, Zheyao and Hu, Xiaolin},
     journal = {Neurocomputing},
     volume = {564},
     pages = {126923},
     year = {2024},
     publisher = {Elsevier}
   }

   

2023

1. TPAMI

   Recognizing Object by Components With Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks

   Xiao Li, Ziqi Wang, Bo Zhang, Fuchun Sun, and Xiaolin Hu

   IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023

   Bib arXiv Code

   @article{rock,
     author = {Li, Xiao and Wang, Ziqi and Zhang, Bo and Sun, Fuchun and Hu, Xiaolin},
     title = {Recognizing Object by Components With Human Prior Knowledge Enhances
                       Adversarial Robustness of Deep Neural Networks},
     journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
     volume = {45},
     number = {7},
     pages = {8861--8873},
     year = {2023}
   }

   

2022

1. IJCV

   Improving Image Segmentation with Boundary Patch Refinement

   Xiaolin Hu, Chufeng Tang, Hang Chen, Xiao Li, Jianmin Li, and Zhaoxiang Zhang

   International Journal of Computer Vision (IJCV), 2022

   Bib

   @article{hu2022improving,
     link = {https://link.springer.com/article/10.1007/s11263-022-01662-0},
     title = {Improving Image Segmentation with Boundary Patch Refinement},
     author = {Hu, Xiaolin and Tang, Chufeng and Chen, Hang and Li, Xiao and Li, Jianmin and Zhang, Zhaoxiang},
     journal = {International Journal of Computer Vision (IJCV)},
     volume = {130},
     number = {11},
     pages = {2571--2589},
     year = {2022},
     publisher = {Springer}
   }

   

2021

1. CVPR

   Look closer to segment better: Boundary patch refinement for instance segmentation

   Chufeng Tang, Hang Chen, Xiao Li, Jianmin Li, Zhaoxiang Zhang, and Xiaolin Hu

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

   Bib Code

   @inproceedings{tang2021look,
     title = {Look closer to segment better: Boundary patch refinement for instance segmentation},
     author = {Tang, Chufeng and Chen, Hang and Li, Xiao and Li, Jianmin and Zhang, Zhaoxiang and Hu, Xiaolin},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {13926--13935},
     year = {2021}
   }

   

2. AAAI

   Fooling thermal infrared pedestrian detectors in real world using small bulbs

   Xiaopei Zhu, Xiao Li, Jianmin Li, Zheyao Wang, and Xiaolin Hu

   In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021

   Bib

   @inproceedings{zhu2021fooling,
     link = {https://ojs.aaai.org/index.php/AAAI/article/view/16477},
     title = {Fooling thermal infrared pedestrian detectors in real world using small bulbs},
     author = {Zhu, Xiaopei and Li, Xiao and Li, Jianmin and Wang, Zheyao and Hu, Xiaolin},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
     volume = {35},
     number = {4},
     pages = {3616--3624},
     year = {2021}
   }