publications | Jiacheng Zhao

2026

Ave: Guiding Agentic GPU Optimization using Data-Flow Invariants

Haohui Mai, Xiaoyan Guo, Xiangyun Ding, and 7 more authors

The 32nd ACM Symposium on Operating Systems Principles (SOSP 2026), to appear, Jul 2026

Bib

@article{pub29,
  title = {Ave: Guiding Agentic GPU Optimization using Data-Flow Invariants},
  author = {Mai, Haohui and Guo, Xiaoyan and Ding, Xiangyun and Li, Daifeng and Yu, Qiuchu and Guo, Chenzhun and Wang, Cong and Zhao, Jiacheng and Kozyrakis, Christos and Yuan, Binhang},
  journal = {The 32nd ACM Symposium on Operating Systems Principles (SOSP 2026), to appear},
  year = {2026},
  month = jul,
}

When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output

Shuoming Zhang, Jiacheng Zhao, Hanyuan Dong, and 9 more authors

The ACM Conference on Computer and Communications Security (CCS 2026), to appear, May 2026

Bib

@article{pub27,
  title = {When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output},
  author = {Zhang, Shuoming and Zhao, Jiacheng and Dong, Hanyuan and Xu, Ruiyuan and Li, Zhicheng and Zhang, Yangyu and Li, Shuaijiang and Wen, Yuan and Xia, Chunwei and Wang, Zheng and Feng, Xiaobing and Cui, Huimin},
  journal = {The ACM Conference on Computer and Communications Security (CCS 2026), to appear},
  year = {2026},
  month = may,
}

Symbiotic MLLM Serving: Dynamically Balancing Parallelism Across GPUs and Resources Within GPUs

Zhicheng Li, Jiacheng Zhao, Yangyu Zhang, and 10 more authors

The 53rd Annual International Symposium on Computer Architecture (ISCA 2026), to appear, May 2026

Bib

@article{pub23,
  title = {Symbiotic MLLM Serving: Dynamically Balancing Parallelism Across GPUs and Resources Within GPUs},
  author = {Li, Zhicheng and Zhao, Jiacheng and Zhang, Yangyu and Duan, Zhaolin and Liu, Xinyu and Li, Siqi and Zhang, Shuoming and Li, Shuaijiang and Yu, Donglin and Wen, Yuan and Xia, Chunwei and Shi, Xiyu and Cui, Huimin},
  journal = {The 53rd Annual International Symposium on Computer Architecture (ISCA 2026), to appear},
  year = {2026},
  month = may,
}

LEGO: An LLM-Enabled Hierarchical Optimizer for Tensor Computation Graphs with Structure-Aware Search and Compositional Synthesis

Ruiyuan Xu, Shuoming Zhang, Guangli Li, and 10 more authors

International Conference on Machine Learning (ICML 2026), to appear, May 2026

Bib

@article{pub26,
  title = {LEGO: An LLM-Enabled Hierarchical Optimizer for Tensor Computation Graphs with Structure-Aware Search and Compositional Synthesis},
  author = {Xu, Ruiyuan and Zhang, Shuoming and Li, Guangli and Yu, Qiuchu and Zhang, Rui and Zhang, Yangyu and Qian, Hao and Xia, Chunwei and Zhao, Jiacheng and Wang, Chenxi and Feng, Xiaobing and Xue, Jingling and Cui, Huimin},
  journal = {International Conference on Machine Learning (ICML 2026), to appear},
  year = {2026},
  month = may,
}

CONTINUUM: Restoring the Contiguous Tensor Abstraction Efficiently for Dynamic AI Workloads via Hardware Virtualization

Yangyu Zhang, Shuoming Zhang, Chunwei Xia, and 10 more authors

International Conference on Machine Learning (ICML 2026), Spotlight (top 2.2%), to appear, May 2026

Bib

@article{pub25,
  title = {CONTINUUM: Restoring the Contiguous Tensor Abstraction Efficiently for Dynamic AI Workloads via Hardware Virtualization},
  author = {Zhang, Yangyu and Zhang, Shuoming and Xia, Chunwei and Li, Shuaijiang and Li, Zhicheng and Xu, Ruiyuan and Yang, Zheming and Chen, Lei and Wen, Yuan and Li, Guangli and Feng, Xiaobing and Cui, Huimin and Zhao, Jiacheng},
  journal = {International Conference on Machine Learning (ICML 2026), Spotlight (top 2.2%), to appear},
  year = {2026},
  month = may,
}

A GPU Memory Allocator with Device-Side Page Table Materialization and Deferred TLB Coherence

Yangyu Zhang, Lei Chen, Chunwei Xia, and 12 more authors

USENIX Symposium on Operating Systems Design and Implementation (OSDI 2026), to appear, May 2026

Bib

@article{pub24,
  title = {A GPU Memory Allocator with Device-Side Page Table Materialization and Deferred TLB Coherence},
  author = {Zhang, Yangyu and Chen, Lei and Xia, Chunwei and Li, Shuaijiang and Zhang, Shuoming and Li, Zhicheng and Sun, Qianqi and Xiao, Jiawei and Xu, Ruiyuan and Chen, Ao and Li, Guangli and Feng, Xiaobing and Cui, Huimin and Wang, Chenxi and Zhao, Jiacheng},
  journal = {USENIX Symposium on Operating Systems Design and Implementation (OSDI 2026), to appear},
  year = {2026},
  month = may,
}

From Threads to Tiles: T2T, a Compiler for CUDA-to-NPU Translation via 2D Vectorization

Shuaijiang Li, Jiacheng Zhao, Ying Liu, and 11 more authors

The 24th ACM/IEEE International Symposium on Code Generation and Optimization (CGO 2026), Distinguished Paper Award, Feb 2026

Bib

@article{pub16,
  title = {From Threads to Tiles: T2T, a Compiler for CUDA-to-NPU Translation via 2D Vectorization},
  author = {Li, Shuaijiang and Zhao, Jiacheng and Liu, Ying and Zhang, Shuoming and Chen, Lei and Li, Yijin and Zhang, Yangyu and Li, Zhicheng and Zhou, Runyu and Shi, Xiyu and Xia, Chunwei and Wen, Yuan and Feng, Xiaobing and Cui, Huimin},
  journal = {The 24th ACM/IEEE International Symposium on Code Generation and Optimization (CGO 2026), Distinguished Paper Award},
  year = {2026},
  month = feb,
}

2025

SpaceServe: Spatial Multiplexing of Complementary Encoders and Decoders for Multimodal LLMs

Zhicheng Li, Shuoming Zhang, Jiacheng Zhao, and 8 more authors

The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), Dec 2025

Bib

@article{pub18,
  title = {SpaceServe: Spatial Multiplexing of Complementary Encoders and Decoders for Multimodal LLMs},
  author = {Li, Zhicheng and Zhang, Shuoming and Zhao, Jiacheng and Li, Siqi and Shi, Xiyu and Zhang, Yangyu and Li, Shuaijiang and Yu, Donglin and Yang, Zheming and Wen, Yuan and Cui, Huimin},
  journal = {The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)},
  year = {2025},
  month = dec
}

Beyond Prompts: Space-Time Decoupling Control-Plane Jailbreaks in LLM Structured Output

Shuoming Zhang, Jiacheng Zhao, Hanyuan Dong, and 5 more authors

arXiv preprint arXiv:2503.24191 (2025), Mar 2025

Bib

@article{pub20,
  title = {Beyond Prompts: Space-Time Decoupling Control-Plane Jailbreaks in LLM Structured Output},
  author = {Zhang, Shuoming and Zhao, Jiacheng and Dong, Hanyuan and Xu, Ruiyuan and Li, Zhicheng and Zhang, Yangyu and Li, Shuaijiang and et al.},
  journal = {arXiv preprint arXiv:2503.24191 (2025)},
  year = {2025},
  month = mar
}

TopServe: Task-Operator Co-scheduling for Efficient Multi-DNN Inference Serving on GPUs

Ao Chen, Guangli Li, Feng Yu, and 5 more authors

European Conference on Parallel Processing, pp. 292-305. Cham: Springer Nature Switzerland, 2025, Jan 2025

Bib

@article{pub21,
  title = {TopServe: Task-Operator Co-scheduling for Efficient Multi-DNN Inference Serving on GPUs},
  author = {Chen, Ao and Li, Guangli and Yu, Feng and Wang, Xueying and Zhao, Jiacheng and Cui, Huimin and Feng, Xiaobing and Xue, Jingling},
  journal = {European Conference on Parallel Processing, pp. 292-305. Cham: Springer Nature Switzerland, 2025},
  year = {2025},
  month = jan
}

Qiwu: Exploiting Ciphertext-Level SIMD Parallelism in Homomorphic Encryption Programs

Zhongcheng Zhang, Ying Liu, Yuyang Zhang, and 5 more authors

Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization (CGO 2025), pp. 523-537, Jan 2025

Bib

@article{pub19,
  title = {Qiwu: Exploiting Ciphertext-Level SIMD Parallelism in Homomorphic Encryption Programs},
  author = {Zhang, Zhongcheng and Liu, Ying and Zhang, Yuyang and Chen, Zhenchuan and Zhao, Jiacheng and Feng, Xiaobing and Cui, Huimin and Xue, Jingling},
  journal = {Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization (CGO 2025), pp. 523-537},
  year = {2025},
  month = jan
}

Fast and scalable neural network quantum states method for molecular potential energy surfaces

Yangjun Wu, Wanlu Cao, Jiacheng Zhao, and 1 more author

IEEE Transactions on Parallel and Distributed Systems (2025), Jan 2025

Bib

@article{pub22,
  title = {Fast and scalable neural network quantum states method for molecular potential energy surfaces},
  author = {Wu, Yangjun and Cao, Wanlu and Zhao, Jiacheng and Shang, Honghui},
  journal = {IEEE Transactions on Parallel and Distributed Systems (2025)},
  year = {2025},
  month = jan
}

2024

Introducing compiler semantics into large language models as programming language translators: A case study of C to x86 assembly

Shuoming Zhang, Jiacheng Zhao, Chunwei Xia, and 3 more authors

Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 996-1011, Nov 2024

Bib

@article{pub17,
  title = {Introducing compiler semantics into large language models as programming language translators: A case study of C to x86 assembly},
  author = {Zhang, Shuoming and Zhao, Jiacheng and Xia, Chunwei and Wang, Zheng and Chen, Yunji and Cui, Huimin},
  journal = {Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 996-1011},
  year = {2024},
  month = nov
}

Optimizing Dynamic-Shape Neural Networks on Accelerators via On-the-Fly Micro-Kernel Polymerization

Feng Yu, Guangli Li, Jiacheng Zhao, and 3 more authors

29th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2024), Apr 2024

Bib

@article{pub15,
  title = {Optimizing Dynamic-Shape Neural Networks on Accelerators via On-the-Fly Micro-Kernel Polymerization},
  author = {Yu, Feng and Li, Guangli and Zhao, Jiacheng and Cui, Huimin and Feng, Xiaobing and Xue, Jingling},
  journal = {29th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2024)},
  year = {2024},
  month = apr
}

Optimizing Deep Learning Inference via Global Analysis and Tensor Expressions

Chunwei Xia, Jiacheng Zhao, Qianqi Sun, and 5 more authors

29th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2024), Apr 2024

Bib

@article{pub13,
  title = {Optimizing Deep Learning Inference via Global Analysis and Tensor Expressions},
  author = {Xia, Chunwei and Zhao, Jiacheng and Sun, Qianqi and Wang, Zheng and Wen, Yuan and Yu, Teng and Feng, Xiaobing and Cui, Huimin},
  journal = {29th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2024)},
  year = {2024},
  month = apr
}

Enabling Large Dynamic Neural Network Training with Learning-based Memory Management

Jie Ren, Dong Xu, Shuangyan Yang, and 6 more authors

30th IEEE International Symposium on High-Performance Computer Architecture (HPCA 2024), Mar 2024

Bib

@article{pub14,
  title = {Enabling Large Dynamic Neural Network Training with Learning-based Memory Management},
  author = {Ren, Jie and Xu, Dong and Yang, Shuangyan and Zhao, Jiacheng and Li, Zhicheng and Navasca, Christian and Wang, Chenxi and Xu, Harry and Li, Dong},
  journal = {30th IEEE International Symposium on High-Performance Computer Architecture (HPCA 2024)},
  year = {2024},
  month = mar
}

2023

Honeycomb: Secure and Efficient GPU Executions via Static Validation

Haohui Mai, Jiacheng Zhao, Hongren Zheng, and 7 more authors

7th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23), Jul 2023

Bib PDF

@article{pub12,
  title = {Honeycomb: Secure and Efficient GPU Executions via Static Validation},
  author = {Mai, Haohui and Zhao, Jiacheng and Zheng, Hongren and Zhao, Yiyang and Liu, Zibin and Gao, Mingyu and Wang, Cong and Cui, Huimin and Feng, Xiaobing and Kozyrakis, Christos},
  journal = {7th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)},
  year = {2023},
  month = jul,
}

Sirius: Harvesting Whole-Program Optimization Opportunities for DNNs

Yijin Li, Jiacheng Zhao, Qianqi Sun, and 12 more authors

Sixth Conference on Machine Learning and Systems (MLSYS), Jun 2023

Bib PDF

@article{pub3,
  title = {Sirius: Harvesting Whole-Program Optimization Opportunities for  DNNs},
  author = {Li, Yijin and Zhao, Jiacheng and Sun, Qianqi and Mai, Haohui and Chen, Lei and Cao, Wanlu and Chen, Yanfan and Li, Zhicheng and Liu, Ying and Zhang, Xinyuan and Shi, Xiyu and Zhao, Jie and Xue, Jingling and Cui, Huimin and Feng, Xiaobing},
  journal = {Sixth Conference on Machine Learning and Systems (MLSYS)},
  year = {2023},
  month = jun,
}

PosFuzz: Augmenting Greybox Fuzzing with Effective Position Distribution

Yanyan Zou, Wei Huo, Jiacheng Zhao, and 3 more authors

Cybersecurity, Jan 2023

Bib

@article{pub11,
  title = {PosFuzz: Augmenting Greybox Fuzzing with Effective Position Distribution},
  author = {Zou, Yanyan and Huo, Wei and Zhao, Jiacheng and Zhang, Yu and Shi, Ji and Zou, Wei},
  journal = {Cybersecurity},
  year = {2023},
  month = jan
}

2022

Unified holistic memory management supporting multiple big data processing frameworks over hybrid memories

Lei Chen, Jiacheng Zhao, Chenxi Wang, and 8 more authors

ACM Transactions on Computer Systems, Jul 2022

Bib PDF

@article{newpub,
  title = {Unified holistic memory management supporting multiple big data processing frameworks over hybrid memories},
  author = {Chen, Lei and Zhao, Jiacheng and Wang, Chenxi and Cao, Ting and Zigman, John and Volos, Haris and Mutlu, Onur and Lv, Fang and Feng, Xiaobing and Xu, Guoqing Harry and Cui, Huimin},
  journal = {ACM Transactions on Computer Systems},
  year = {2022},
  month = jul,
}

VTensor: Using Virtual Tensors to Build a Layout-Oblivious AI Programming Framework (Full Version)

Feng Yu, Jiacheng Zhao, Huimin Cui, and 2 more authors

Journal of Computer Science and Technology, Apr 2022

Bib PDF

@article{pub5,
  title = {VTensor: Using Virtual Tensors to Build a Layout-Oblivious AI Programming Framework (Full Version)},
  author = {Yu, Feng and Zhao, Jiacheng and Cui, Huimin and Feng, Xiaobing and Xue, Jingling},
  journal = {Journal of Computer Science and Technology},
  year = {2022},
  month = apr,
}

2020

VTensor: Using Virtual Tensors to Build a Layout-Oblivious AI Programming Framework (Poster Version)

Feng Yu, Jiacheng Zhao, Huimin Cui, and 2 more authors

PACT ’20: Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques, Sep 2020

Bib PDF

@article{pub4,
  title = {VTensor: Using Virtual Tensors to Build a Layout-Oblivious AI Programming Framework (Poster Version)},
  author = {Yu, Feng and Zhao, Jiacheng and Cui, Huimin and Feng, Xiaobing and Xue, Jingling},
  journal = {PACT '20: Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques},
  year = {2020},
  month = sep,
}

2019

DNNTune: Automatic benchmarking DNN models for mobile-cloud computing

Chunwei Xia, Jiacheng Zhao, Huimin Cui, and 2 more authors

ACM Transactions on Architecture and Code Optimization, Dec 2019

Bib PDF Code

@article{pub1,
  title = {DNNTune: Automatic benchmarking DNN models for mobile-cloud computing},
  author = {Xia, Chunwei and Zhao, Jiacheng and Cui, Huimin and Feng, Xiaobing and Xue, Jingling},
  journal = {ACM Transactions on Architecture and Code Optimization},
  year = {2019},
  month = dec,
}

2018

On retargeting the ai programming framework to new hardwares

Jiacheng Zhao, Yisong Chang, Denghui Li, and 4 more authors

Network and Parallel Computing: 15th IFIP WG 10.3 International Conference, NPC 2018, Nov 2018

Bib PDF

@article{pub6,
  title = {On retargeting the ai programming framework to new hardwares},
  author = {Zhao, Jiacheng and Chang, Yisong and Li, Denghui and Xia, Chunwei and Cui, Huimin and Zhang, Ke and Feng, Xiaobing},
  journal = {Network and Parallel Computing: 15th IFIP WG 10.3 International Conference, NPC 2018},
  year = {2018},
  month = nov,
}

Characterizing DNN models for edge-cloud computing (Poster)

Chunwei Xia, Jiacheng Zhao, Huimin Cui, and 1 more author

2018 IEEE International Symposium on Workload Characterization (IISWC), Sep 2018

Bib PDF

@article{pub10,
  title = {Characterizing DNN models for edge-cloud computing (Poster)},
  author = {Xia, Chunwei and Zhao, Jiacheng and Cui, Huimin and Feng, Xiaobing},
  journal = {2018 IEEE International Symposium on Workload Characterization (IISWC)},
  year = {2018},
  month = sep,
}

Revisiting loop tiling for datacenters: live and let live

Jiacheng Zhao, Huimin Cui, Yalin Zhang, and 2 more authors

ICS ’18: Proceedings of the 2018 International Conference on Supercomputing, Jun 2018

Bib PDF

@article{pub2,
  title = {Revisiting loop tiling for datacenters: live and let live},
  author = {Zhao, Jiacheng and Cui, Huimin and Zhang, Yalin and Xue, Jingling and Feng, Xiaobing},
  journal = {ICS '18: Proceedings of the 2018 International Conference on Supercomputing},
  year = {2018},
  month = jun,
}

2016

Predicting cross-core performance interference on multicore processors with regression analysis

Jiacheng Zhao, Huimin Cui, Jingling Xue, and 1 more author

IEEE Transactions on Parallel and Distributed Systems , May 2016

Bib PDF

@article{pub7,
  title = {Predicting cross-core performance interference on multicore processors with regression analysis},
  author = {Zhao, Jiacheng and Cui, Huimin and Xue, Jingling and Feng, Xiaobing},
  journal = {IEEE Transactions on Parallel and Distributed Systems },
  year = {2016},
  month = may,
}

2015

Hadoop+: Modeling and Evaluating the Heterogeneity for MapReduce Applications in Heterogeneous Clusters

Wenting He, Huimin Cui, Binbin Lu, and 7 more authors

Proceedings of the 29th ACM on International Conference on Supercomputing (ICS), Jun 2015

Bib PDF

@article{pub9,
  title = {Hadoop+: Modeling and Evaluating the Heterogeneity for MapReduce Applications in Heterogeneous Clusters},
  author = {He, Wenting and Cui, Huimin and Lu, Binbin and Zhao, Jiacheng and Li, Shengmei and Ruan, Gong and Xue, Jingling and Feng, Xiaobing and Yang, Wensen and Yan, Youliang},
  journal = {Proceedings of the 29th ACM on International Conference on Supercomputing (ICS)},
  year = {2015},
  month = jun,
}

2013

An empirical model for predicting cross-core performance interference on multicore processors

Jiacheng Zhao, Xiaobing Feng, Huimin Cui, and 3 more authors

Proceedings of the 22nd international conference on Parallel architectures and compilation techniques (PACT), Sep 2013

Bib PDF

@article{pub8,
  title = {An empirical model for predicting cross-core performance interference on multicore processors},
  author = {Zhao, Jiacheng and Feng, Xiaobing and Cui, Huimin and Yan, Youliang and Xue, Jingling and Yang, Wensen},
  journal = {Proceedings of the 22nd international conference on Parallel architectures and compilation techniques (PACT)},
  year = {2013},
  month = sep,
}