Fan Lai

Orcid: 0009-0005-0472-107X

Affiliations:

University of Illinois Urbana-Champaign, IL, USA
University of Michigan, Department of Electronic Engineering and Computer Science, Ann Arbor, MI, USA (PhD 2023)
Shanghai Jiaotong University, Department of Electronic Engineering, China (former)

According to our database¹, Fan Lai authored at least 43 papers between 2016 and 2025.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of three.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2025

OPPO: Accelerating PPO-based RLHF via Pipeline Overlap.

[BibT_eX]

[DOI]

CoRR, September, 2025

CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems.

[BibT_eX]

[DOI]

CoRR, September, 2025

Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models.

[BibT_eX]

[DOI]

CoRR, June, 2025

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts.

[BibT_eX]

[DOI]

CoRR, June, 2025

Single-agent or Multi-agent Systems? Why Not Both?

[BibT_eX]

[DOI]

CoRR, May, 2025

Tempo: Application-aware LLM Serving with Mixed SLO Requirements.

[BibT_eX]

[DOI]

CoRR, April, 2025

Circinus: Efficient Query Planner for Compound ML Serving.

[BibT_eX]

[DOI]

CoRR, April, 2025

Sequoia: An Accessible and Extensible Framework for Privacy-Preserving Machine Learning over Distributed Data.

[BibT_eX]

[DOI]

Proc. ACM Manag. Data, February, 2025

HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location.

[BibT_eX]

[DOI]

Ting Sun

Penghan Wang

Fan Lai

CoRR, January, 2025

EchoLM: Accelerating LLM Serving with Real-time Knowledge Distillation.

[BibT_eX]

[DOI]

CoRR, January, 2025

IC-Cache: Efficient Large Language Model Serving via In-context Caching.

[BibT_eX]

[DOI]

Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles, 2025

DiSCo: Device-Server Collaborative LLM-based Text Streaming Services.

[BibT_eX]

[DOI]

Ting Sun

Penghan Wang

Fan Lai

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

Fed-ensemble: Ensemble Models in Federated Learning for Improved Generalization and Uncertainty Quantification.

[BibT_eX]

[DOI]

IEEE Trans Autom. Sci. Eng., July, 2024

Mercury: QoS-Aware Tiered Memory System.

[BibT_eX]

[DOI]

CoRR, 2024

Disaggregating Embedding Recommendation Systems with FlexEMR.

[BibT_eX]

[DOI]

CoRR, 2024

Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services.

[BibT_eX]

[DOI]

CoRR, 2024

Learn To be Efficient: Build Structured Sparsity in Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems.

[BibT_eX]

[DOI]

CoRR, 2024

Learn To be Efficient: Build Structured Sparsity in Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

FedTrans: Efficient Federated Learning via Multi-Model Transformation.

[BibT_eX]

[DOI]

Proceedings of the Seventh Annual Conference on Machine Learning and Systems, 2024

2023

Minimalist Systems for Pervasive Machine Learning

[BibT_eX]

[DOI]

Fan Lai

PhD thesis, 2023

Venn: Resource Management Across Federated Learning Jobs.

[BibT_eX]

[DOI]

CoRR, 2023

AdaEmbed: Adaptive Embedding for Large-Scale Recommendation Models.

[BibT_eX]

[DOI]

Chun-cheng Jason Chen

Mosharaf Chowdhury

Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation, 2023

ModelKeeper: Accelerating DNN Training via Automated Training Warmup.

[BibT_eX]

[DOI]

Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation, 2023

Coverage-centric Coreset Selection for High Pruning Rates.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing.

[BibT_eX]

[DOI]

Proceedings of the Eighteenth European Conference on Computer Systems, 2023

Flamingo: A User-Centric System for Fast and Energy-Efficient DNN Training on Smartphones.

[BibT_eX]

[DOI]

Sanjay Sri Vallabh Singapuram

Proceedings of the 4th International Workshop on Distributed Machine Learning, 2023

Auxo: Efficient Federated Learning via Scalable Client Clustering.

[BibT_eX]

[DOI]

Proceedings of the 2023 ACM Symposium on Cloud Computing, SoCC 2023, 2023

2022

Auxo: Heterogeneity-Mitigating Federated Learning via Scalable Client Clustering.

[BibT_eX]

[DOI]

CoRR, 2022

Swan: A Neural Engine for Efficient DNN Training on Smartphone SoCs.

[BibT_eX]

[DOI]

Sanjay Sri Vallabh Singapuram

Fan Lai

Chuheng Hu

Mosharaf Chowdhury

CoRR, 2022

Efficient DNN Training with Knowledge-Guided Layer Freezing.

[BibT_eX]

[DOI]

CoRR, 2022

FedScale: Benchmarking Model and System Performance of Federated Learning at Scale.

[BibT_eX]

[DOI]

Fan Lai

Yinwei Dai

Sanjay Sri Vallabh Singapuram

Proceedings of the International Conference on Machine Learning, 2022

2021

Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learning.

[BibT_eX]

[DOI]

CoRR, 2021

FedScale: Benchmarking Model and System Performance of Federated Learning.

[BibT_eX]

[DOI]

CoRR, 2021

FedScale: Benchmarking Model and System Performance of Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the ResilientFL '21: Proceedings of the First Workshop on Systems Challenges in Reliable and Secure Federated Learning, 2021

Oort: Efficient Federated Learning via Guided Participant Selection.

[BibT_eX]

[DOI]

Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation, 2021

2020

Oort: Informed Participant Selection for Scalable Federated Learning.

[BibT_eX]

[DOI]

CoRR, 2020

Sol: Fast Distributed Computation Over Slow Networks.

[BibT_eX]

[DOI]

Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation, 2020

2018

To Relay or Not to Relay for Inter-Cloud Transfers?

[BibT_eX]

[DOI]

Fan Lai

Mosharaf Chowdhury

Harsha V. Madhyastha

Proceedings of the 10th USENIX Workshop on Hot Topics in Cloud Computing, 2018

2017

A Linear Network Code Construction for General Integer Connections Based on the Constraint Satisfaction Problem.

[BibT_eX]

[DOI]

IEEE/ACM Trans. Netw., 2017

2016

Enhanced VIP Algorithms for Forwarding, Caching, and Congestion Control in Named Data Networks.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Global Communications Conference, 2016

Optimal Caching and User Association in Cache-Enabled Heterogeneous Wireless Networks.

[BibT_eX]

[DOI]

Proceedings of the 2016 IEEE Global Communications Conference, 2016

Scaled VIP Algorithms for Joint Dynamic Forwarding and Caching in Named Data Networks.

[BibT_eX]

[DOI]

Proceedings of the 3rd ACM Conference on Information-Centric Networking, 2016

Fan Lai

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...