Publications

2025

1. arXiv

   Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning

   Shaobo Wang , Jiaming Wang , Jiajun Zhang , Cong Wang , Yue Min , Zichen Wen , Fei Huang , Huiqiang Jiang , and 3 more authors

   2025
2. arXiv

   Socratic-Zero : Bootstrapping Reasoning via Data-Free Agent Co-evolution

   Shaobo Wang , Zhengbo Jiao , Zifan Zhang , Yilang Peng , Xu Ze , Boyu Yang , Wei Wang , Hu Wei , and 1 more author

   2025
3. CVPR highlight

   Dataset Distillation with Neural Characteristic Function: A Minmax Perspective

   Shaobo Wang , Yicun Yang , Zhiyuan Liu , Chenghao Sun , Xuming Hu , Conghui He , and Linfeng Zhang

   Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

   Bib PDF Code News (Chinese)

   @article{wang2025dataset,
     title = {Dataset Distillation with Neural Characteristic Function: A Minmax Perspective},
     author = {Wang, Shaobo and Yang, Yicun and Liu, Zhiyuan and Sun, Chenghao and Hu, Xuming and He, Conghui and Zhang, Linfeng},
     year = {2025},
     journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
     news_zh = {https://mp.weixin.qq.com/s/VtIqPF_a098qAEvrTKbi6A}
   }

4. ACL main

   Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning

   Shaobo Wang , Xiangqi Jin , Ziming Wang , Jize Wang , Jiajun Zhang , Kaixin Li , Zichen Wen , Zhong Li , and 3 more authors

   Annual Meeting of the Association for Computational Linguistics, 2025

   Bib PDF Code Website

   @article{wang2025datawhisperer,
     title = {Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning},
     author = {Wang, Shaobo and Jin, Xiangqi and Wang, Ziming and Wang, Jize and Zhang, Jiajun and Li, Kaixin and Wen, Zichen and Li, Zhong and He, Conghui and Hu, Xuming and Zhang, Linfeng},
     year = {2025},
     journal = {Annual Meeting of the Association for Computational Linguistics},
   }

5. ICLR

   Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers

   Shaobo Wang , Hongxuan Tang , Mingyang Wang , Hongrui Zhang , Xuyang Liu , Weiya Li , Xuming Hu , and Linfeng Zhang

   International Conference on Learning Representations, 2025

   Bib PDF Code

   @article{wang2024gnothi,
     title = {Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers},
     author = {Wang, Shaobo and Tang, Hongxuan and Wang, Mingyang and Zhang, Hongrui and Liu, Xuyang and Li, Weiya and Hu, Xuming and Zhang, Linfeng},
     year = {2025},
     primaryclass = {cs.LG},
     journal = {International Conference on Learning Representations},
   }

6. arXiv

   Dd-ranking: Rethinking the evaluation of dataset distillation

   Zekai Li , Xinhao Zhong , Samir Khaki , Zhiyuan Liang , Yuhao Zhou , Mingjia Shi , Ziqiao Wang , Xuanlei Zhao , and 3 more authors

   2025

   Bib PDF Code

   @article{li2025dd,
     title = {Dd-ranking: Rethinking the evaluation of dataset distillation},
     author = {Li, Zekai and Zhong, Xinhao and Khaki, Samir and Liang, Zhiyuan and Zhou, Yuhao and Shi, Mingjia and Wang, Ziqiao and Zhao, Xuanlei and Zhao, Wangbo and Qin, Ziheng and others},
     year = {2025}
   }

7. NeurIPS

   Efficient Multi-modal Large Language Models via Progressive Consistency Distillation

   Zichen Wen , Shaobo Wang , Yufa Zhou , Junyuan Zhang , Qintong Zhang , Yifeng Gao , Zhaorun Chen , Bin Wang , and 3 more authors

   2025

   Bib

   @misc{zhang2025efficient,
     title = {Efficient Multi-modal Large Language Models via Progressive Consistency Distillation},
     author = {Wen, Zichen and Wang, Shaobo and Zhou, Yufa and Zhang, Junyuan and Zhang, Qintong and Gao, Yifeng and Chen, Zhaorun and Wang, Bin and Li, Weijia and He, Conghui and Zhang, Linfeng},
     year = {2025}
   }

8. arXiv

   Shifting AI Efficiency From Model-Centric to Data-Centric Compression

   Xuyang Liu* , Zichen Wen* , Shaobo Wang* , Junjie Chen , Zhishan Tao , Yubo Wang , Xiangqi Jin , Chang Zou , and 8 more authors

   2025

   Bib PDF

   @misc{liu2025shiftingaiefficiencymodelcentric,
     title = {Shifting AI Efficiency From Model-Centric to Data-Centric Compression},
     author = {Liu*, Xuyang and Wen*, Zichen and Wang*, Shaobo and Chen, Junjie and Tao, Zhishan and Wang, Yubo and Jin, Xiangqi and Zou, Chang and Wang, Yiyu and Liao, Chenfei and Zheng, Xu and Chen, Honggang and Li, Weijia and Hu, Xuming and He, Conghui and Zhang, Linfeng},
     year = {2025},
     eprint = {2505.19147},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
   }

9. arXiv

   dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

   Zhiyuan Liu , Yicun Yang , Yaojie Zhang , Junjie Chen , Chang Zou , Qingyan Wei , Shaobo Wang , and Linfeng Zhang

   2025

   Bib PDF Code

   @misc{liu2025dllm,
     title = {dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching},
     author = {Liu, Zhiyuan and Yang, Yicun and Zhang, Yaojie and Chen, Junjie and Zou, Chang and Wei, Qingyan and Wang, Shaobo and Zhang, Linfeng},
     year = {2025},
   }

10. arXiv

    Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs

    Yufa Zhou* , Shaobo Wang* , Xingyu Dong* , Xiangqi Jin , Yifang Chen , Yue Min , Xingzhang Ren , Kexin Yang , and 2 more authors

    2025

    Bib PDF Code

    @misc{recon,
      title = {Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs},
      author = {Zhou*, Yufa and Wang*, Shaobo and Dong*, Xingyu and Jin, Xiangqi and Chen, Yifang and Min, Yue and Ren, Xingzhang and Yang, Kexin and Liu, Dayiheng and Zhang, Linfeng},
      year = {2025},
    }

11. ICLR workshop

    Rethink Dataset Pruning From a Generalization Perspective

    Furui Xu* , Shaobo Wang* , Chenghao Sun , Jiajun Zhang , and Linfeng Zhang

    The Future of Machine Learning Data Practices and Repositories at ICLR 2025, 2025

    Bib PDF

    @article{xu2025unseen,
      title = {Rethink Dataset Pruning From a Generalization Perspective},
      author = {Xu*, Furui and Wang*, Shaobo and Sun, Chenghao and Zhang, Jiajun and Zhang, Linfeng},
      journal = {The Future of Machine Learning Data Practices and Repositories at ICLR 2025},
      year = {2025},
    }

12. EMNLP main

    Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More

    Zichen Wen , Yifeng Gao , Shaobo Wang , Junyuan Zhang , Qintong Zhang , Weijia Li , Conghui He , and Linfeng Zhang

    2025

    Bib PDF

    @article{wen2025stoplookingimportanttokens,
      title = {Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More},
      author = {Wen, Zichen and Gao, Yifeng and Wang, Shaobo and Zhang, Junyuan and Zhang, Qintong and Li, Weijia and He, Conghui and Zhang, Linfeng},
      year = {2025},
      eprint = {2502.11494},
      archiveprefix = {arXiv},
      primaryclass = {cs.CL},
    }

13. ACMMM

    Compute only 16 tokens in one timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching

    Zhixin Zheng , Xinyu Wang , Chang Zou , Shaobo Wang , and Linfeng Zhang

    ACM Multimedia, 2025

    Bib PDF

    @article{zheng2025compute,
      title = {Compute only 16 tokens in one timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching},
      author = {Zheng, Zhixin and Wang, Xinyu and Zou, Chang and Wang, Shaobo and Zhang, Linfeng},
      journal = {ACM Multimedia},
      year = {2025},
    }

14. ACMMM

    SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching

    Jiacheng Liu , Chang Zou , Yuanhuiyi Lyu , Fei Ren , Shaobo Wang , Kaixin Li , and Linfeng Zhang

    ACM Multimedia, 2025

    Bib PDF

    @article{zheng2025computf,
      title = {SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching},
      author = {Liu, Jiacheng and Zou, Chang and Lyu, Yuanhuiyi and Ren, Fei and Wang, Shaobo and Li, Kaixin and Zhang, Linfeng},
      journal = {ACM Multimedia},
      year = {2025},
    }

15. CVPR workshop

    Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation

    Shaobo Wang , Yantai Yang , Qilong Wang , Kaixin Li , Linfeng Zhang , and Junchi Yan

    Synthetic Data for Computer Vision Workshop at CVPR, 2025

    Bib PDF

    @article{wang2024samples,
      title = {Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation},
      author = {Wang, Shaobo and Yang, Yantai and Wang, Qilong and Li, Kaixin and Zhang, Linfeng and Yan, Junchi},
      year = {2025},
      eprint = {2408.12483},
      archiveprefix = {arXiv},
      primaryclass = {cs.CV},
      journal = {Synthetic Data for Computer Vision Workshop at CVPR},
    }

2024

1. ECCV

   Think2Drive: Efficient Reinforcement Learning by Thinking with Latent World Model for Autonomous Driving (in CARLA-V2)

   Qifeng Li , Xiaosong Jia , Shaobo Wang , and Junchi Yan

   European Conference on Computer Vision, 2024

   Bib PDF

   @article{li2024think2drive,
     title = {Think2Drive: Efficient Reinforcement Learning by Thinking with Latent World Model for Autonomous Driving (in CARLA-V2)},
     author = {Li, Qifeng and Jia, Xiaosong and Wang, Shaobo and Yan, Junchi},
     journal = {European Conference on Computer Vision},
     year = {2024},
   }

2. NeurIPS

   Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers

   Siyu Chen , Heejune Sheen , Tianhao Wang , and Zhuoran Yang

   Advances in Neural Information Processing Systems, 2024

   Bib PDF Code

   @article{chen2024unveiling,
     title = {Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers},
     author = {Chen, Siyu and Sheen, Heejune and Wang, Tianhao and Yang, Zhuoran},
     journal = {Advances in Neural Information Processing Systems},
     year = {2024},
   }

3. ICLR workshop

   DRUPI: Dataset Reduction Using Privileged Information

   Shaobo Wang , Yantai Yang , Shuaiyu Zhang , Chenghao Sun , Weiya Li , Xuming Hu , and Linfeng Zhang

   The Future of Machine Learning Data Practices and Repositories at ICLR, 2024

   Bib PDF

   @article{wang2024drupi,
     title = {DRUPI: Dataset Reduction Using Privileged Information},
     author = {Wang, Shaobo and Yang, Yantai and Zhang, Shuaiyu and Sun, Chenghao and Li, Weiya and Hu, Xuming and Zhang, Linfeng},
     year = {2024},
     eprint = {2410.01611},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     journal = {The Future of Machine Learning Data Practices and Repositories at ICLR},
   }

2023

1. arXiv

   Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework

   Shaobo Wang , Xiangdong Zhang , and Junchi Yan

   arXiv preprint arXiv:2311.15993 (arXiv), 2023

   Bib PDF

   @article{wang2023unified,
     title = {Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework},
     author = {Wang, Shaobo and Zhang, Xiangdong and Yan, Junchi},
     year = {2023},
     eprint = {2311.15993},
     archiveprefix = {arXiv},
     primaryclass = {cs.CV},
     journal = {arXiv preprint arXiv:2311.15993 (arXiv)}
   }

2022

1. arXiv

   Trap of Feature Diversity in the Learning of MLPs

   Dongrui Liu* , Shaobo Wang* , Jie Ren , Kangrui Wang , Sheng Yin , Huiqi Deng , and Quanshi Zhang

   arXiv preprint arXiv:2112.00980 (arXiv), 2022

   Bib PDF

   @article{liu2022trap,
     title = {Trap of Feature Diversity in the Learning of MLPs},
     author = {Liu*, Dongrui and Wang*, Shaobo and Ren, Jie and Wang, Kangrui and Yin, Sheng and Deng, Huiqi and Zhang, Quanshi},
     year = {2022},
     eprint = {2112.00980},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     journal = {arXiv preprint arXiv:2112.00980 (arXiv)}
   }

2021

1. NeurIPS

   Visualizing the emergence of intermediate visual patterns in dnns

   Mingjie Li , Shaobo Wang , and Quanshi Zhang

   Advances in Neural Information Processing Systems, 2021

   Bib PDF Code

   @article{li2021visualizing,
     title = {Visualizing the emergence of intermediate visual patterns in dnns},
     author = {Li, Mingjie and Wang, Shaobo and Zhang, Quanshi},
     journal = {Advances in Neural Information Processing Systems},
     volume = {34},
     pages = {6594--6607},
     year = {2021},
   }