Pengfei Zuo

@article{wang2026taiji,
  title = {TaiJi: Unifying Prefill-Decode Disaggregation and Aggregation for Goodput-Optimized LLM Serving},
  author = {Wang, Chao and Zuo, Pengfei and Chen, Zhangyu and Liang, Yunkai and Yu, Zhou and Yang, Ming-Chang},
  journal = {Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)},
  year = {2026},
}

@article{gu2026maze,
  title = {Maze: A Distributed Framework for Large Language Model Agents},
  author = {Gu, Jing and Xing, Zhuang and Yang, Yiheng and Lv, Bowen and Wang, Jiale and Yuan, Shuo and Chen, Zijin and Zhao, Jin and Zuo, Pengfei and Zheng, Long and Liao, Xiaofei and Jin, Hai and Li, Qinbin},
  journal = {Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)},
  year = {2026},
}

@article{wang2026tilesparse,
  title = {TileSparse: Arithmetic-Intensity-Aware Sparse Attention for Compute-Bound LLM Decoding},
  author = {Wang, Chao and Zuo, Pengfei and Chen, Zhangyu and Zhou, Qihui and Ho, Tsung-Yi and Yang, Ming-Chang},
  journal = {Proceedings of the 43rd International Conference on Machine Learning (ICML)},
  year = {2026},
}

@article{qiu2026hyper,
  title = {HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction},
  author = {Qiu, Shengxuan and Huang, Haochen and Zhong, Shuzhang and Zuo, Pengfei and Li, Meng},
  journal = {Proceedings of the 43rd International Conference on Machine Learning (ICML)},
  year = {2026},
}

@article{zhong2026spec,
  title = {Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration},
  author = {Zhong, Shuzhang and Huang, Haochen and Qiu, Shengxuan and Zuo, Pengfei and Wang, Runsheng and Li, Meng},
  journal = {Proceedings of the 20th USENIX Symposium on Operating Systems Design and Implementation (OSDI)},
  year = {2026},
}

@article{zhou2026sparseserve,
  title = {SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving},
  author = {Zhou, Qihui and Yin, Peiqi and Zuo, Pengfei and Cheng, James},
  journal = {Proceedings of the 40th ACM International Conference on Supercomputing (ICS)},
  year = {2026},
}

@article{yuan2026dualmap,
  title = {DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving},
  author = {Yuan, Ying and Zuo, Pengfei and Wang, Bo and Chen, Zhangyu and Tan, Zhipeng and Yu, Zhou},
  journal = {Proceedings of the 14th International Conference on Learning Representations (ICLR)},
  year = {2026},
}

@article{Zuo2025ServingLL,
  title = {Serving Large Language Models on Huawei CloudMatrix384},
  author = {Zuo, Pengfei and Lin, Huimin and Deng, Junbo and Zou, Nan and Xingkun Yang and Yingyu Diao and Weifeng Gao and Ke Xu and Zhangyu Chen and Shirui Lu and Zhao Qiu and Peiyang Li and Xianyu Chang and Zhengzhong Yu and Fangzheng Miao and Jia Zheng and Ying Li and Yuan Feng and Bei Wang and Zaijian Zong and Mosong Zhou and Wenli Zhou and Houjiang Chen and Xingyu Liao and Yipeng Li and Wenxiao Zhang and Ping Zhu and Yinggang Wang and Chuanjie Xiao and Depeng Liang and Dong Cao and Juncheng Liu and Yongqiang Yang and Xiaolong Bai and Yi Li and Huaguo Xie and Huatao Wu and Zhibin Yu and Lv Chen and Hu Liu and Yujun Ding and Haipei Zhu and Jing Xia and Yi Xiong and Zhou Yu and Heng Liao},
  journal = {arXiv preprint arXiv:2506.12708},
  year = {2025},
}

@article{Liang2025InjectingAI,
  title = {Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation},
  author = {Liang, Yunkai and Chen, Zhangyu and Zuo, Pengfei and Zhou, Zhi and Chen, Xu and Yu, Zhou},
  journal = {arXiv preprint arXiv:2503.20552},
  year = {2025},
}

@article{Zhou2025ProgressiveSA,
  title = {Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving},
  author = {Zhou, Qihui and Yin, Peiqi and Zuo, Pengfei and Cheng, James},
  journal = {arXiv preprint arXiv:2503.00392},
  year = {2025},
}

@inproceedings{Gao2024CostEfficientLL,
  title = {Cost‑Efficient Large Language Model Serving for Multi‑turn Conversations with CachedAttention},
  author = {Gao, Bin and He, Zhuomin and Sharma, Puru and Kang, Qingxuan and Jevdjic, Djordje and Deng, Junbo and Yang, Xingkun and Yu, Zhou and Zuo, Pengfei},
  booktitle = {Proceedings of the 2024 USENIX Annual Technical Conference (USENIX ATC)},
  year = {2024},
}

@inproceedings{Hu2024AcesoAA,
  title = {Aceso: Achieving Efficient Fault Tolerance in Memory‑Disaggregated Key‑Value Stores},
  author = {Hu, Zhisheng and Zuo, Pengfei and Chen, Yizou and Wang, Chao and Hu, Junliang and Yang, Ming‑Chang},
  booktitle = {Proceedings of the 30th ACM Symposium on Operating Systems Principles (SOSP)},
  year = {2024},
}

@inproceedings{Luo2024CHIMEA,
  title = {CHIME: A Cache‑Efficient and High‑Performance Hybrid Index on Disaggregated Memory},
  author = {Luo, Xuchuan and Shen, Jiacheng and Zuo, Pengfei and Wang, Xin and Lyu, Michael R. and Zhou, Yangfan},
  booktitle = {Proceedings of the 30th ACM Symposium on Operating Systems Principles (SOSP)},
  year = {2024},
}

@inproceedings{Shen2023DittoAE,
  title = {Ditto: An Elastic and Adaptive Memory‑Disaggregated Caching System},
  author = {Shen, Jiacheng and Zuo, Pengfei and Luo, Xuchuan and Su, Yuxin and Gu, Jiazhen and Feng, Hao and Zhou, Yangfan and Lyu, Michael R.},
  booktitle = {Proceedings of the 29th ACM Symposium on Operating Systems Principles (SOSP)},
  year = {2023},
}

@inproceedings{Luo2023SMARTA,
  title = {SMART: A High‑Performance Adaptive Radix Tree for Disaggregated Memory},
  author = {Luo, Xuchuan and Zuo, Pengfei and Shen, Jiacheng and Gu, Jiazhen and Wang, Xin and Lyu, Michael R. and Zhou, Yangfan},
  booktitle = {Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI)},
  year = {2023},
}

@inproceedings{Li2023ROLEXAS,
  title = {ROLEX: A Scalable RDMA‑oriented Learned Key‑Value Store for Disaggregated Memory Systems},
  author = {Li, Pengfei and Hua, Yu and Zuo, Pengfei and Chen, Zhangyu and Sheng, Jiajie},
  booktitle = {Proceedings of the 21st USENIX Conference on File and Storage Technologies (FAST)},
  year = {2023},
}

@inproceedings{Shen2023FUSEEAF,
  title = {FUSEE: A Fully Memory‑Disaggregated Key‑Value Store},
  author = {Shen, Jiacheng and Zuo, Pengfei and Luo, Xuchuan and Yang, Tianyi and Su, Yuxin and Zhou, Yangfan and Lyu, Michael R.},
  booktitle = {Proceedings of the 21st USENIX Conference on File and Storage Technologies (FAST)},
  year = {2023},
}

@inproceedings{Zhang2022FORDFO,
  title = {FORD: Fast One‑sided RDMA‑based Distributed Transactions for Disaggregated Persistent Memory},
  author = {Zhang, Ming and Hua, Yu and Zuo, Pengfei and Liu, Lurong},
  booktitle = {Proceedings of the 20th USENIX Conference on File and Storage Technologies (FAST)},
  year = {2022},
}

@inproceedings{Li2022FINEdexAF,
  title = {FINEdex: A Fine‑grained Learned Index Scheme for Scalable and Concurrent Memory Systems},
  author = {Li, Pengfei and Hua, Yu and Jia, Jingnan and Zuo, Pengfei},
  booktitle = {Proceedings of the 48th International Conference on Very Large Data Bases (VLDB)},
  year = {2022},
}

@inproceedings{Zuo2021SEALingNN,
  title = {SEALing Neural Network Models in Encrypted Deep Learning Accelerators},
  author = {Zuo, Pengfei and Hua, Yu and Liang, Ling and Xie, Xingfeng and Hu, Xing and Xie, Yuan},
  booktitle = {Proceedings of the 58th Design Automation Conference (DAC)},
  year = {2021},
}

@inproceedings{Zuo2021OnesidedRE,
  title = {One-sided RDMA-Conscious Extendible Hashing for Disaggregated Memory},
  author = {Zuo, Pengfei and Sun, Jiazhao and Yang, Liu and Zhang, Shuangwu and Hua, Yu},
  booktitle = {Proceedings of the USENIX Annual Technical Conference (USENIX ATC)},
  year = {2021},
}

@inproceedings{Chen2020LockfreeCL,
  title = {Lock-free Concurrent Level Hashing for Persistent Memory},
  author = {Chen, Zhangyu and Hua, Yu and Ding, Bo and Zuo, Pengfei},
  booktitle = {Proceedings of the USENIX Annual Technical Conference (USENIX ATC)},
  year = {2020},
}

@inproceedings{Hu2020DeepSnifferAD,
  title = {DeepSniffer: a DNN Model Extraction Framework Based on Learning Architectural Hints},
  author = {Hu, Xing and Liang, Ling and Li, Shuangchen and Deng, Lei and Zuo, Pengfei and Ji, Yu and Xie, Xinfeng and Ding, Yufei and Liu, Chang and Sherwood, Timothy and Xie, Yuan},
  booktitle = {Proceedings of the 25th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
  year = {2020},
}

@inproceedings{Zuo2019SuperMemEA,
  title = {SuperMem: Enabling Application-transparent Secure Persistent Memory with Low Overheads},
  author = {Zuo, Pengfei and Hua, Yu and Xie, Yuan},
  booktitle = {Proceedings of the 52nd IEEE/ACM International Symposium on Microarchitecture (MICRO)},
  year = {2019},
}

@inproceedings{Zuo2018ImprovingTP,
  title = {Improving the Performance and Endurance of Encrypted Non-volatile Main Memory through Deduplicating Writes},
  author = {Zuo, Pengfei and Hua, Yu and Zhao, Ming and Zhou, Wen and Guo, Yuncheng},
  booktitle = {Proceedings of the 51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)},
  year = {2018},
}

@inproceedings{Zuo2018WriteOptimizedAH,
  title = {Write-Optimized and High-Performance Hashing Index Scheme for Persistent Memory},
  author = {Zuo, Pengfei and Hua, Yu and Wu, Jie},
  booktitle = {Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI)},
  year = {2018},
}