Shaobo Wang (王少博)

@misc{wang2025rethinkingllmevaluationevaluate,
  title = {Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data?},
  author = {Wang, Shaobo and Wang, Cong and Fu, Wenjie and Min, Yue and Feng, Mingquan and Guan, Isabel and Hu, Xuming and He, Conghui and Wang, Cunxiang and Yang, Kexin and Ren, Xingzhang and Huang, Fei and Liu, Dayiheng and Zhang, Linfeng},
  booktitle = {The Fourteenth International Conference on Learning Representations},
  year = {2026},
  url = {https://openreview.net/forum?id=lZlZjSxdio}
}

@article{wang2026grounding,
  title = {Grounding and Enhancing Informativeness and Utility in Dataset Distillation},
  author = {Wang, Shaobo and Yang, Yantai and Chen, Guo and Li, Peiru and Li, Kaixin and Zhou, Yufa and andLinfeng Zhang, Zhaorun Chen},
  journal = {The Fourteenth International Conference on Learning Representations},
  year = {2026},
  url = {https://openreview.net/forum?id=ThsYRbpv2F}
}

@inproceedings{liu2026bridging,
  title = {Bridging Visual Dynamics and Narrative Reasoning: Multimodal Large Language Models for Short Drama Quality Assessment},
  author = {Liu, Qingyang and Li, Jiangtong and Peng, Zelin and Wang, Shaobo and Liao, Zhaohe and Chang, Shuochen and Gao, Bingjie and Zhao, Haonan and Liu, Mu and Jiang, Jidong and Niu, Li},
  booktitle = {The ACM Web Conference 2026 Industry Track},
  year = {2026},
  url = {https://openreview.net/forum?id=Fkwvsf7U8N},
}

@article{xu2026unseen,
  title = {UNSEEN: Enhancing Dataset Pruning from a Generalization Perspective},
  author = {Xu*, Furui and Wang*, Shaobo and Zhang, Jiajun and Sun, Chenghao and Tang, Haixiang and Zhang, Linfeng},
  journal = {Annual AAAI Conference on Artificial Intelligence},
  year = {2026},
}

@article{min2026imagebinddc,
  title = {ImagebindDC: Compressing Multimodal Data with Imagebind-based Condensation},
  author = {Min*, Yue and Wang*, Shaobo and Li, Jiaze and Niu, Tianle and Fan, Junxin and Miao, Yongliang and Yang, Lijin and Zhang, Linfeng},
  journal = {Annual AAAI Conference on Artificial Intelligence},
  year = {2026},
}

@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}
}

@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},
}

@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},
}

@misc{wang2025videocompressa,
  title = {VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction},
  author = {Wang, Shaobo and Niu, Tianle and Yang, Runkang and Liu, Deshan and He, Xu and Wen, Zichen and He, Conghui and Hu, Xuming and Zhang, Linfeng},
  year = {2025},
  eprint = {2511.18831},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2511.18831}
}

@misc{wang2025circuitseermininghighqualitydata,
  title = {CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs},
  author = {Wang, Shaobo and Miao, Yongliang and Liu, Yuancheng and and Qianli Ma and Liao, Ning and Zhang, Linfeng},
  year = {2025},
  eprint = {2510.18470},
  archiveprefix = {arXiv},
  primaryclass = {cs.AI},
  url = {https://arxiv.org/abs/2510.18470},
}

@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}
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}

@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},
}