Yanying Lin (林彦颖)

Postdoc@Harvard

Email: yylin1039@gmail.com

Yanying Lin is currently a postdoctoral researcher in Prof. Minlan Yu’s group at Harvard University. He received his Ph.D. in Computer Science from the University of Chinese Academy of Sciences (UCAS), where he worked with Prof. Kejiang Ye and Prof. Cheng-Zhong Xu. He previously visited the UPenn and UCSD. His research focuses on Heterogeneous-Native AI Infrastructure.

Research & Collaborations

Heterogeneous-Native AI Infrastructure addresses mixed accelerators, uneven networks, and dynamic AI workloads through communication, runtime, and HW/SW co-design: how tokens and activations cross network and device boundaries, how serving runtimes refactor pipelines as load and topology change, and how software is designed with the hardware that actually runs inference and agents.

He has collaborated with distinguished scholars in the systems community, including Prof. Rong Chen (SJTU), Prof. Xinyu Zhang (UCSD), Prof. Vincent Liu (UPenn), and Prof. Minlan Yu (Harvard).

Earlier visits took this into elastic agent inference at UPenn and FPGA-GPU acceleration for LLM serving at UCSD.

news

Aug 19, 2026

Receive the CCF (Distributed Computing TC) Outstanding Doctoral Dissertation (优博) 🏆

Jun 16, 2026

Honored to receive the CAS President’s Special Award (中国科学院院长特别奖)! 🏆

May 12, 2026

One paper accepted to SIGCOMM’26.

Apr 03, 2026

One paper accepted to TPDS and one to ISCA’26!

Oct 14, 2025

We released GenTD26, a production-level top-down dataset for serverless diffusion model serving!

view all news →

selected publications

SIGCOMM26

Connex: Endpoint Mobility Primitives for Dynamic LLM Serving

Yanying Lin, Vincent Liu, Tao Luo, Chengzhong Xu, and Kejiang Ye

In Proceedings of the ACM SIGCOMM Conference, 2026

Bib HTML PDF Slides

@inproceedings{lin2026connex,
  title = {Connex: Endpoint Mobility Primitives for Dynamic LLM Serving},
  author = {Lin, Yanying and Liu, Vincent and Luo, Tao and Xu, Chengzhong and Ye, Kejiang},
  booktitle = {Proceedings of the ACM SIGCOMM Conference},
  year = {2026},
}

ISCA26

DynoPipe: Heterogeneous Edge-Cloud LLM Serving with Dynamically Orchestrated Pipeline Boundaries

Yanying Lin, Baicheng Chen, Xinyu Zhang, Chengzhong Xu, and Kejiang Ye

In Proceedings of the 53rd International Symposium on Computer Architecture, 2026

Bib HTML PDF Slides

@inproceedings{lin2026dynopipe,
  title = {DynoPipe: Heterogeneous Edge-Cloud LLM Serving with Dynamically Orchestrated Pipeline Boundaries},
  author = {Lin, Yanying and Chen, Baicheng and Zhang, Xinyu and Xu, Chengzhong and Ye, Kejiang},
  booktitle = {Proceedings of the 53rd International Symposium on Computer Architecture},
  year = {2026},
}

EuroSys26
FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters

Yanying Lin, Shijie Peng, Chengzhi Lu, Chengzhong Xu, and Kejiang Ye

In Proceedings of the 21st European Conference on Computer Systems, 2026

Insight Bib HTML PDF

Insight: We find that for pipeline inference, the optimal online pipeline structure varies greatly depending on the incoming request distribution. Longer pipelines can absorb load spikes by dispersing demand, while shorter pipelines reduce communication overhead. Dynamically adjusting the pipeline structure according to the request distribution is an effective approach in serverless environments.
@inproceedings{lin2026flexpipe, title = {FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters}, author = {Lin, Yanying and Peng, Shijie and Lu, Chengzhi and Xu, Chengzhong and Ye, Kejiang}, booktitle = {Proceedings of the 21st European Conference on Computer Systems}, year = {2026}, }
SoCC25
Understanding Diffusion Model Serving in Production: A Top-Down Analysis of Workload, Scheduling, and Resource Efficiency

Yanying Lin, Shuaipeng Wu, Shutian Luo, Hong Xu, Haiying Shen, Chong Ma, Min Shen, Le Chen, Chengzhong Xu, Lin Qu, and Kejiang Ye

In Proceedings of the 2025 ACM Symposium on Cloud Computing, 2025

Insight Bib PDF Slides

Insight: The main insights of this work are obtained from production systems. It focuses on the performance of online inference, middleware, and hardware layers, as well as the relationships between these three components. We find that skewed request distributions force systems to stress network and cache layers, resulting in poor resource locality and reduced system performance.
@inproceedings{lin2025understanding, title = {Understanding Diffusion Model Serving in Production: A Top-Down Analysis of Workload, Scheduling, and Resource Efficiency}, author = {Lin, Yanying and Wu, Shuaipeng and Luo, Shutian and Xu, Hong and Shen, Haiying and Ma, Chong and Shen, Min and Chen, Le and Xu, Chengzhong and Qu, Lin and Ye, Kejiang}, booktitle = {Proceedings of the 2025 ACM Symposium on Cloud Computing}, pages = {1--15}, year = {2025}, }
ICDCS24
Quart: Latency-Aware FaaS System for Pipelining Large Model Inference

Yanying Lin, Yanbo Li, Shijie Peng, Yingfei Tang, Shutian Luo, Haiying Shen, Chengzhong Xu, and Kejiang Ye

In Proceedings of the 44th IEEE International Conference on Distributed Computing Systems, 2024

Insight Bib PDF

Insight: We find that when using pipeline inference for LLMs, each stage exhibits significant load differences due to varying resource allocation and throughput across different workloads. For example, under stable or bursty traffic patterns, throughput disparities between upstream and downstream stages can create performance-critical bottlenecks in the pipeline.
@inproceedings{lin2024quart, title = {Quart: Latency-Aware FaaS System for Pipelining Large Model Inference}, author = {Lin, Yanying and Li, Yanbo and Peng, Shijie and Tang, Yingfei and Luo, Shutian and Shen, Haiying and Xu, Chengzhong and Ye, Kejiang}, booktitle = {Proceedings of the 44th IEEE International Conference on Distributed Computing Systems}, year = {2024}, }