Haozhi Han (韩昊知)

Ph.D. Student @ PKUCS

haozhi.han AT stu.pku.edu.cn

nathan_hhz

Hi! I am Haozhi Han (韩昊知), a Ph.D. student at the School of Computer Science, Peking University, advised by Prof. Yifeng Chen and Assistant Prof. Kun Li.

🔬 My research advances Scientific AI, High-Performance Computing, and Agentic Systems, spanning AI foundations, scalable scientific algorithms, and autonomous discovery. I seek to redefine what we can compute and discover with AI.

🏆 My work has appeared at premier venues including SC, NeurIPS, PPoPP, and ISC, with an SC 2025 Best Student Paper nomination.

🤝 Looking for long-term collaborators in Scientific AI, High-Performance Computing, and Agentic Systems. 🙋 Feel free to reach out via email.

📃 Selected Papers

PPoPP ’27

EvoCG: Self-Evolving Precision Control for Faster Conjugate Gradient

Jiaqi Zhai^*, Haozhi Han^*, Kaiyi Huang, Wenju Zhao, Yifeng Chen, Yunquan Zhang, Ting Cao, Yunxin Liu, Hai Jin, Xuanhua Shi, and Kun Li (* equal contribution)

CCF-A

In Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (PPoPP), 2027

arXiv Bib

@inproceedings{evocg2027ppopp,
  publication_category = {published},
  homepage_publication = {true},
  title = {EvoCG: Self-Evolving Precision Control for Faster Conjugate Gradient},
  author = {Zhai, Jiaqi and Han, Haozhi and Huang, Kaiyi and Zhao, Wenju and Chen, Yifeng and Zhang, Yunquan and Cao, Ting and Liu, Yunxin and Jin, Hai and Shi, Xuanhua and Li, Kun},
  booktitle = {Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (PPoPP)},
  year = {2027},
  rank = {CCF-A}
}

SC ’26

MakoXC: Rearchitecting DFT Exchange–Correlation with Matrix-Aligned and Knowledge-Organized Sparsity

Haozhi Han, Fusong Ju, Jing Bai, Ruge Zhang, Xiang Zhao, Liang Yuan, Yunquan Zhang, Ting Cao, Liu Yunxin, Yifeng Chen, and Kun Li

CCF-A

In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2026

Presented at CCF HPC China 2026
Research Spotlight from Tsinghua AIR

Paper arXiv Bib

@inproceedings{makoxc2026sc,
  publication_category = {published},
  homepage_publication = {true},
  title = {MakoXC: Rearchitecting DFT Exchange–Correlation with Matrix-Aligned and Knowledge-Organized Sparsity},
  author = {Han, Haozhi and Ju, Fusong and Bai, Jing and Zhang, Ruge and Zhao, Xiang and Yuan, Liang and Zhang, Yunquan and Cao, Ting and Yunxin, Liu and Chen, Yifeng and Li, Kun},
  booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC)},
  year = {2026},
  note = {<span class="pub-feature-label">Presented at</span> <a class="pub-feature-link" href="https://ccf.org.cn/hpcchina2026/schedule_d_4013" target="_blank" rel="noopener">CCF HPC China 2026</a><br><span class="pub-feature-label">Research Spotlight from</span> <a class="pub-feature-link" href="https://mp.weixin.qq.com/s/JwN5XQppjFvLexsnEe-UhA?utm_source=chatgpt.com" target="_blank" rel="noopener">Tsinghua AIR</a>},
  rank = {CCF-A}
}

SC ’25

Matrix Is All You Need: Rearchitecting Computational Chemistry to Scale on AI Accelerators

Haozhi Han, Kun Li, Fusong Ju, Qi Li, Yifeng Chen, Yunquan Zhang, Ting Cao, and Mao Yang

CCF-A

In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2025

Featured by Microsoft Academic Collaboration Official

DOI Bib

@inproceedings{matrix2025sc,
  publication_category = {published},
  homepage_publication = {true},
  title = {Matrix Is All You Need: Rearchitecting Computational Chemistry to Scale on AI Accelerators},
  author = {Han, Haozhi and Li, Kun and Ju, Fusong and Li, Qi and Chen, Yifeng and Zhang, Yunquan and Cao, Ting and Yang, Mao},
  booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC)},
  year = {2025},
  doi = {10.1145/3712285.3759829},
  note = {<span class="pub-feature-label">Featured by</span> <a class="pub-feature-link" href="https://mp.weixin.qq.com/s/t3LFewL9gZ_5Y3atrdpv1A" target="_blank" rel="noopener">Microsoft Academic Collaboration Official</a>},
  rank = {CCF-A}
}

SC ’25

SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation

Qi Li, Kun Li, Haozhi Han, Liang Yuan, Junshi Chen, Yunquan Zhang, Yifeng Chen, Hong An, Ting Cao, and Mao Yang

CCF-A🏆 Best Student Paper Award Finalist

In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2025

DOI Bib

@inproceedings{sparstencil2025sc,
  publication_category = {published},
  homepage_publication = {true},
  title = {SparStencil: Retargeting Sparse Tensor Cores to Scientific Stencil Computations via Structured Sparsity Transformation},
  author = {Li, Qi and Li, Kun and Han, Haozhi and Yuan, Liang and Chen, Junshi and Zhang, Yunquan and Chen, Yifeng and An, Hong and Cao, Ting and Yang, Mao},
  booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC)},
  year = {2025},
  doi = {10.1145/3712285.3759820},
  honor = {🏆 Best Student Paper Award Finalist},
  rank = {CCF-A}
}

PPoPP ’25

FlashFFTStencil: Bridging Fast Fourier Transforms to Memory-Efficient Stencil Computations on Tensor Core Units

Haozhi Han, Kun Li, Wei Cui, Donglin Bai, Yiwei Zhang, Liang Yuan, Yifeng Chen, Yunquan Zhang, Ting Cao, and Mao Yang

CCF-A

In Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (PPoPP), 2025

Presented at CCF HPC China 2025

DOI Bib

@inproceedings{flashfftstencil2025ppopp,
  publication_category = {published},
  homepage_publication = {true},
  title = {FlashFFTStencil: Bridging Fast Fourier Transforms to Memory-Efficient Stencil Computations on Tensor Core Units},
  author = {Han, Haozhi and Li, Kun and Cui, Wei and Bai, Donglin and Zhang, Yiwei and Yuan, Liang and Chen, Yifeng and Zhang, Yunquan and Cao, Ting and Yang, Mao},
  booktitle = {Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (PPoPP)},
  year = {2025},
  doi = {10.1145/3710848.3710897},
  note = {<span class="pub-feature-label">Presented at</span> <a class="pub-feature-link" href="https://ccf.org.cn/hpcchina2025/schedule_d_2007" target="_blank" rel="noopener">CCF HPC China 2025</a>},
  rank = {CCF-A}
}

Haozhi Han @ PKU

📃 Selected Papers