| Home | Full Bio | Publications (by topic; by date) | Talks | Teaching | Students | Services | Software | Funding |
Publications by topic
Some of our conference video talks are available here at our group video channel
- Systems for LLM inference
- Systems for distributed deep learning
- Machine learning for systems
- Energy efficient computing
- Accelerate distributed systems using eBPF
- SmartNIC
- Programmable measurement architecture
- Diagnosis for cloud applications
- Programmable switches
- Verification and synthesis
- Data center network management
- Job scheduling
- Cloud computing
- Internet
Systems for LLM inference
- (SIGCOMM shorts) HKVQ: Homomorphic KV Quantization for Disaggregated LLM ServingZeyu Zhang, Haiying Shen, Shay Vargaftik, Ran Ben Basat, Michael Mitzenmacher and Minlan YuACM SIGCOMM shortSep. 2025
[ paper ][ slides ] - (MLSys) NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM InferenceXuanlin Jiang, Yang Zhou, Shiyi Cao, Ion Stoica and Minlan YuEighth Conference on Machine Learning and Systems (MLSys)May 2025
[ paper ][ slides ] - (ICLR) Don’t Stop Me Now: Embedding Based Scheduling for LLMsRana Shahout, Eran Malach, Chunwei Liu, Weifan Jiang, Minlan Yu and Michael MitzenmacherInternational Conference on Learning Representations (ICLR)Apr. 2025
[ paper ][ poster ] - (SLLM) Prefix and Output Length-Aware Scheduling for Efficient Online LLM InferenceIñaki Arango, Ayush Noori, Yepeng Huang, Rana Shahout and Minlan YuICLR workshop on Sparsity in LLMs: Deep Dive into Mixture of Experts, Quantization, Hardware, and Inference (SLLM)Apr. 2025
[ paper ][ poster ] - (SLLM) Faster, Cheaper, Just As Good: Cost- and Latency-Constrained Routing For LLMSJavid Lakha, Minlan Yu and Rana ShahoutICLR workshop on Sparsity in LLMs: Deep Dive into Mixture of Experts, Quantization, Hardware, and Inference (SLLM)Apr. 2025
[ paper ]
Systems for distributed deep learning
- (ATC) Bumblebee: Accelerating Multi-Modal LLM Training at Scale by Bubble ExploitationWeiqi Feng, Yangrui Chen, Shaoyu Wang, Yanghua Peng, Haibin Lin and Minlan YuUSENIX Annual Technical Conference (ATC)Jul. 2025
[ paper ][ slides ] - (NSDI) Minder: Faulty Machine Detection for Large-scale Distributed Model TrainingYangtao Deng, Xiang Shi, Zhuo Jiang, Xingjian Zhang, Lei Zhang, Zhang Zhang, Bo Li, Zuquan Song, Hang Zhu, Gaohong Liu, Fuliang Li, Shuguang Wang, Haibin Lin, Jianxi Ye and Minlan YuUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2025
[ paper ][ slides ] - (NSDI) THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic CompressionMinghao Li, Ran Ben Basat, Shay Vargaftik, ChonLam Lao, Kevin Xu, Michael Mitzenmacher and Minlan YuUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2024
[ paper ][ slides ]
Machine learning for systems
- (SIGCOMM) Intent-Driven Network Management with Multi-Agent LLMs: The Confucius FrameworkZhaodong Wang, Samuel Lin, Guanqing Yan, Soudeh Ghorbani, Minlan Yu, Jiawei Zhou, Nathan Hu, Lopa Baruah, Sam Peters, Srikanth Kamath, Jerry Yang and Ying ZhangACM SIGCOMMSep. 2025
[ paper ][ slides ] - (OSDI) Decouple and Decompose: Scaling Resource Allocation through a Different LensZhiying Xu, Francis Yan and Minlan YuUSENIX Symposium on Operating Systems Design and Implementation (OSDI)Jul. 2025
[ paper ][ slides ] - (SIGCOMM) Teal: Learning\-Ac\-cel\-er\-at\-ed Optimization of WAN Traffic EngineeringZhiying Xu, Francis Yan, Rachee Singh, Justin Chiu, Alexander Rush and Minlan YuProc. ACM SIGCOMMAug. 2024
[ paper ][ slides ][ video ] - (SIGCOMM) Teal: Learning\-Ac\-cel\-er\-at\-ed Optimization of WAN Traffic EngineeringZhiying Xu, Francis Yan, Rachee Singh, Justin Chiu, Alexander Rush and Minlan YuACM SIGCOMMAug. 2023
[ paper ][ slides ][ video ] - (CONEXT) Boosting Existing DDoS Detection Systems Using Auxiliary SignalsZhiying Xu, Sivaramakrishnan Ramanathan, Alexander Rush, Jelena Mirkovic and Minlan YuACM SIGCOMM International Conference on emerging Networking EXperiments and Technologies (CoNEXT)Dec. 2022
[ paper ][ slides ] - (NDSS) BLAG: Improving Accuracy of BlacklistsSivaramakrishnan Ramanathan, Jelena Mirkovic and Minlan YuNetwork and Distributed System Security Symposium (NDSS)Feb. 2020
[ paper ][ slides ]
Energy-efficient computing
- A View of the Sustainable Computing LandscapeBenjamin C. Lee, David Brooks, Arthur van Benthem, Udit Gupta, Gage Hills, Vincent Liu, Linh Thi Xuan Phan, Benjamin Pierce, Christopher Stewart, Emma Strubell, Gu-Yeon Wei, Adam Wierman, Yuan Yao and Minlan YuCell Patterns2025
[paper]
Accelerate distributed systems using eBPF
- (NSDI) eTran: Extensible Kernel Transport with eBPFZhongjie Chen, Qingkai Meng, ChonLam Lao, Yifan Liu, Fengyuan Ren, Minlan Yu and Yang ZhouUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2025
[ paper ][ slides ] - (NSDI) DINT: Fast In-Kernel Distributed Transactions with eBPFYang Zhou, Xingyu Xiang, Matthew Kiley, Sowmya Dharanipragada and Minlan YuUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2024
[ paper ][ slides ] - (NSDI) Electrode: Accelerating Distributed Protocols with eBPFYang Zhou, Zezhou Wang, Sowmya Dharanipragada and Minlan YuUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2023
[ paper ][ slides ]
SmartNICs
- (NSDI) Rearchitecting the TCP Stack for I/O-Offloaded Content DeliveryTaehyun Kim, Deondre Martin Ng, Junzhi Gong, Youngjin Kwon, Minlan Yu and KyoungSoo ParkUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2023
[ paper ][ slides ]
Programmable measurement architecture
- (CoNEXT) F3: Fast and Flexible Network Telemetry with an FPGA coprocessorWeiqi Feng, Jiaqi Gao, Xiaoqi Chen, Gianni Antichi, Ran Ben Basat, Michael Mingchao Shao, Ying Zhang and Minlan YuACM SIGCOMM International Conference on emerging Networking EXperiments and Technologies (CoNEXT)Dec. 2024
[ paper ][ slides ] - (ICDE) BitMatcher: Bit-level Counter Adjustment for SketchesQilong Shi, Chengjun Jia, Wenjun Li, Zaoxing Liu, Tong Yang, Jianan Ji, Gaogang Xie, Weizhe Zhang and Minlan YuIEEE International Conference on Data Engineering (ICDE)May 2024
[ paper ][ slides ] - (SIGCOMM) Direct Telemetry AccessJonatan Langlet, Ran Ben Basat, Gabriele Oliaro, Michael Mitzenmacher, Minlan Yu and Gianni AntichiACM SIGCOMMAug. 2023
[ paper ][ slides ][ video ] - (NSDI) Evolvable Network Telemetry at FacebookYang Zhou, Ying Zhang, Minlan Yu, Guangyu Wang, Dexter Cao, Eric Sung and Starsky WongUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2022
[ paper ][ slides ] - (HotNets) Zero-CPU Collection with Direct Telemetry AccessJonatan Langlet, Ran Ben Basat, Sivaram Ramanathan, Gabriele Oliaro, Michael Mitzenmacher, Minlan Yu and Gianni AntichiACM Workshop on Hot Topics in Networks (HotNets)2021
[ paper ][ slides ] - (CONEXT) Detecting Routing Loops in the Data PlaneJan Kučera, Ran Ben Basat, Mario Kuka, Gianni Antichi, Minlan Yu and Michael MitzenmacherACM SIGCOMM International Conference on emerging Networking EXperiments and Technologies (CoNEXT)Dec. 2020
[ paper ][ slides ] - (SIGCOMM) PINT: Probabilistic In-band Network TelemetryRan Ben Basat, Sivaramakrishnan Ramanathan, Yuliang Li, Gianni Antichi, Minlan Yu and Michael MitzenmacherACM SIGCOMM (Also published as highlights in SYSTOR’21: ACM International Systems and Storage Conference)Aug. 2020
[ paper ][ long slides ][ long video ] - (IFIP) Routing Oblivious Measurement AnalyticsRan Ben Basat, Xiaoqi Chen, Gil Einziger, Shir Landau Feibish, Danny Raz and Minlan YuIFIP the International Federation for Information Processing NetworkingJun. 2020
[ paper ] - (CCR) Network Telemetry: Towards A Top-Down ApproachMinlan YuACM SIGCOMM Computer Communication Review (Editorial)2019
[paper] - (CCR) Accelerating Network Measurement in SoftwareYang Zhou, Omid Alipoufard, Minlan Yu and Tong YangACM SIGCOMM Computer Communication Review2018
[paper] - (HotNets) Re-evaluating Measurement Algorithms in SoftwareOmid Alipourfard, Masoud Moshref and Minlan YuACM Workshop on Hot Topics in Networks (HotNets)2015
[ paper ][ slides ] - (JNSM) HONE: Joint Host-Network Traffic Management in Software-Defined NetworksPeng Sun, Minlan Yu, Michael J. Freedman, Jennifer Rexford and David WalkerJournal of Network and Systems Management (JNSM), special issue on software-defined networkingJul. 2014
[paper] - (HotSDN) Resource/Accuracy Tradeoffs in Software-Defined MeasurementMasoud Moshref, Minlan Yu and Ramesh GovindanACM SIGCOMM Workshop on Hot Topics in Software Defined Networking (HotSDN)2013
[ paper ][ slides ] - (HotICE) Online measurement of large traffic aggregates on commodity switchesLavanya Jose, Minlan Yu and Jennifer RexfordUSENIX workshop on Hot Topics in Management of Internet, Cloud, and Enterprise Networks and Services2011
[ paper ][ slides ]
Diagnosis for cloud applications
- (SIGCOMM) Microscope: Queue-based Performance Diagnosis for Network FunctionsJunzhi Gong, Yuliang Li, Bilal Anwer, Aman Shaikh and Minlan YuACM SIGCOMMAug. 2020
[ paper ][ long slides ][ short slides ] - (SIGCOMM) Scouts: Improving the Diagnosis Process Through Domain-customized Incident RoutingJiaqi Gao, Nofel Yaseen, Robert MacDavid, Felipe Vieira Frujeri, Vincent Liu, Ricardo Bianchini, Ramaswamy Aditya, Xiaohang Wang, Henry Lee, David Maltz, Minlan Yu and Behnaz ArzaniACM SIGCOMMAug. 2020
[ paper ][ long slides ][ short slides ] - (NSDI) DETER: Deterministic TCP Replay for Performance DiagnosisYuliang Li, Rui Miao, Mohammad Alizadeh and Minlan YuUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Feb. 2019
[ paper ][ slides ][ code ]
Programmable switches
- (ATC) Hashing Design in Modern Networks: Challenges and Mitigation TechniquesYunhong Xu, Keqiang He, Rui Wang, Minlan Yu, Nick Duffield, Hassan Wassel, Shidong Zhang, Leon Poutievski, Junlan Zhou and Amin VahdatUSENIX Annual Technical Conference (ATC)Jul. 2022
[ paper ][ slides ] - (USENIX Security) Jaqen: A High-Performance Switch-Native Approach for Detecting and Mitigating Volumetric DDoS Attacks with Programmable SwitchesZaoxing Liu, Hun Namkung, Georgios Nikolaidis, Jeongkeun Lee, Changhoon Kim, Xin Jin, Vladimir Braverman, Minlan Yu and Vyas SekarUSENIX Security Symposium (USENIX Security)Aug. 2021
[ paper ][ slides ] - (SIGMOD) Cheetah: Accelerating Database Queries with Switch PruningMuhammad Tirmazi, Ran Ben Basat, Jiaqi Gao and Minlan YuSIGMODJun. 2020
[ paper ][ slides ][ full tech report ][ code ][ video ] - (HotNets) Challenging the Stateless Quo of Programmable SwitchesNadeen Gebara, Alberto Lerner, Mingran Yang, Minlan Yu, Paolo Costa and Manya GhobadiACM Workshop on Hot Topics in Networks (HotNets)2020
[ paper ][ slides ] - (SIGCOMM) HPCC: High Precision Congestion Control for RDMAYuliang Li, Rui Miao, Hongqiang Liu, Yan Zhuang, Fei Feng, Lingbo Tang, Zheng Cao, Frank Kelly, Mohammad Alizadeh, Minlan Yu and Ming ZhangACM SIGCOMMAug. 2019
[ paper ][ slides ][ code ] - (CCR) NOSIX: A Lightweight Portability Layer for the SDN OSMinlan Yu, Andreas Wundsam and Muruganantham RajuACM SIGCOMM Computer Communication ReviewApr. 2014
[paper] - (HotSDN) Flow-level State Transition as a New Switch Primitive for SDNMasoud Moshref, Apoorv Bhargava, Adhip Gupta, Minlan Yu and Ramesh GovindanACM SIGCOMM Workshop on Hot Topics in Software Defined Networking (HotSDN)2014
[ paper ][ slides ]
Verification and Synthesis
- (NSDI) Practical Intent-driven Routing Configuration SynthesisSivaramakrishnan Ramanathan, Ying Zhang, Mohab Gawish, Yogesh Mundada, Zhaodong Wang, Sangki Yun, Eric Lippert, Walid Taha, Minlan Yu and Jelena MirkovicUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2023
[ paper ][ slides ] - (SIGCOMM) SwitchV: Automated SDN Switch Validation with P4 ModelsKinan Dak Albab, Steffen Smolka, Jonathan Dilorenzo, Ali Kheradmand, Konstantin Weitz, Stefan Heule, Minlan Yu, Jiaqi Gao and Muhammad TirmaziACM SIGCOMMAug. 2022
[ paper ][ video ] - (SIGCOMM) Aquila: A Practically Usable Verification System for Production-Scale Programmable Data PlanesBingchuan Tian, Jiaqi Gao, Mengqi Liu, Ennan Zhai, Yanqing Chen, Yu Zhou, Li Dai, Feng Yan, Mengjing Ma, Ming Tang, Jie Lu, Xionglie Wei, Hongqiang Harry Liu, Ming Zhang, Chen Tian and Minlan YuACM SIGCOMMAug. 2021
[ paper ][ long slides ][ short slides ] - (SIGCOMM) Lyra: A Cross-Platform Language and Compiler for Data Plane Programming on Heterogeneous ASICsJiaqi Gao, Ennan Zhai, Hongqiang Harry Liu, Rui Miao, Yu Zhou, Bingchuan Tian, Chen Sun, Dennis Cai, Ming Zhang and Minlan YuACM SIGCOMMAug. 2020
[ paper ][ long slides ][ short slides ][ short video ]
Data center network management
- (NSDI) Preventing Network Bottlenecks: Accelerating Datacenter Services with Hotspot-Aware Placement for Compute and StorageHamid Bazzaz, Weiwu Pang, Yingjie Bi, Minlan Yu, Ramesh Govindan, Neal Cardwell, Nandita Dukkipati, Meng-Jung Tsai, Chris DeForeest, Yuxue Jin, Charles Carver, Jan Kopański, Liqun Cheng and Amin VahdatUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2025
[ paper ][ slides ] - (TON) Optimal Oblivious Routing with Concave Objectives for Structured NetworksKanatip Chitavisutthivong, Sucha Supittayapornpong, Pooria Namyar, Mingyang Zhang, Minlan Yu and Ramesh GovindanIEEE/ACM Trasactions on Networking (TON)2023
[paper] - (OSDI) Carbink: Fault-tolerant far memoryYang Zhou, Hassan Wassel, Sihang Liu, Jiaqi Gao, James Mickens, Minlan Yu, Chris Kennelly, Paul Turner, David Culler, Hank Levy and Amin VahdatUSENIX Symposium on Operating Systems Design and Implementation (OSDI) (Also published The Third Workshop On Resource Disaggregation and Serverless Computing (WORDS22))Jul. 2022
[ paper ][ slides ] - (INFOCOM) Optimal Oblivious Routing for Structured NetworksPooria Namyar, Sucha Supittayapornpong, Mingyang Zhang, Minlan Yu and Ramesh GovindanIEEE INFOCOMMay 2022
[ paper ][ slides ] - (SIGCOMM) A Throughput-Centric View of the Performance of Datacenter TopologiesPooria Namyar, Sucha Supit\-taya\-porn\-pong, Mingyang Zhang, Minlan Yu and Ramesh GovindanACM SIGCOMMAug. 2021
[ paper ][ long slides ][ short slides ][ code ] - (OSDI) Sundial: Fault-tolerant Clock-synchronization for DatacentersYuliang Li, Gautam Kumar, Hema Hariharan, Hassan Wassel, Peter Hochschild, Dave Platt, Simon Sabato, Minlan Yu, Nandita Dukkipati, Prashant Chandra and Amin VahdatUSENIX Symposium on Operating Systems Design and Implementation (OSDI)Nov. 2020
[ paper ][ slides ] - (SOSP) Risk-based planning for evolving data-center networksOmid Alipourfard, Jiaqi Gao, Jeremie Koenig, Chris Harshaw, Amin Vahdat and Minlan YuSymposium on operating systems principles (SOSP)Oct. 2019
[ paper ][ slides ][ code ] - (HotNets) Decoupling algorithms and optimizations in network functionsOmid Alipourfard and Minlan YuACM Workshop on Hot Topics in Networks (HotNets)Nov. 2018
[ paper ][ slides ] - (CompNet) Joint VM placement and topology optimization for traffic scalability in dynamic datacenter networksYangming Zhao, Yifan Huang, Kai Chen, Minlan Yu, Sheng Wang and DongSheng LiComputer Networks2015
[paper] - (HotSDN) A Secure Computation Framework for Software Defined NetworksNachikethas A. Jagadeesan, Ranjan Pal, Kaushik Nadikuditi, Yan Huang, Elaine Shi and Minlan Yuposter in ACM SIGCOMM Workshop on Hot Topics in Software Defined Networking2014
[ abstract ][ poster ] - (HotSDN) FlowTags: Enforcing Network-Wide Policies in the Presence of Dynamic Middlebox ActionsSeyed Fayazbakhsh, Vyas Sekar, Minlan Yu and Jeff MogulACM SIGCOMM Workshop on Hot Topics in Software Defined Networking (HotSDN)2013
[ paper ][ slides ] - (HotCloud) VCRIB: Virtualized rule management in the cloudMasoud Moshref, Minlan Yu, Abhishek Sharma and Ramesh GovindanUSENIX Workshop on Hot Topics in Cloud Computing (HotCloud)2012
[ paper ][ slides ][ poster ] - (commag) A Survey of virtual LAN usage in campus networksMinlan Yu, Xin Sun, Nick Feamster, Sanjay Rao and Jennifer RexfordIEEE Communications MagazineJul. 2011
[paper] - Scalable management of enterprise and data-center networksMinlan YuPh.D. Thesis (ACM SIGCOMM Doctoral Dissertation Award)2011
[ paper ][ slides ] - (HotNets) CloudPolice: Taking Access Control out of the NetworkLucian Popa, Minlan Yu, Steven Y. Ko, Sylvia Ratnasamy and Ion StoicaACM Workshop on Hot Topics in Networks (HotNets)2010
[ paper ][ slides ] - (WREN) Hash, Don’t Cache: Fast Packet Forwarding for Enterprise Edge RoutersMinlan Yu and Jennifer RexfordProc. ACM SIGCOMM Workshop on Research in Enterprise Networks (WREN)2009
[ paper ][ slides ] - (CCR) Rethinking virtual network embedding: Substrate support for path splitting and migrationMinlan Yu, Yung Yi, Jennifer Rexford and Mung ChiangACM SIGCOMM Computer Communication ReviewApr. 2008
[ paper ]
Job scheduling
- (MAMA) Speculation-Aware Cluster SchedulingXiaoqi Ren, Ganesh Ananthanarayanan, Adam Wierman and Minlan YuWorkshop on MAthematical performance Modeling and Analysis (MAMA)2015
[ paper ]
Cloud computing
Internet
- (ASPLOS) OctoCache: Caching Voxels for Accelerating 3D Occupancy Mapping in Autonomous SystemsPeiqing Chen, Minghao Li, Zishen Wan, Yu-Shun Hsiao, Minlan Yu, Vijay Janapa Reddi and Zaoxing LiuACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)Apr. 2025
[ paper ][ slides ] - (MetaCom) Challenges in Metaverse Research: An Internet of Things PerspectiveTarek Abdelzaher, Matthew Caesar, Charith Mendis, Klara Nahrstedt, Mani Srivastava and Minlan YuIEEE International Conference on Metaverse Computing Networking and ApplicationsJun. 2023
[ paper ] - (NSDI) Scalable Distributed Massive MIMO Baseband ProcessingJunzhi Gong, Anuj Kalia and Minlan YuUSENIX Symposium on Networked Systems Design and Implementation (NSDI)Apr. 2023
[ paper ][ slides ] - (IMC) Quantifying the Impact of Blacklisting in the Age of Address ReuseSivaramakrishnan Ramanathan, Anushah Hossain, Jelena Mirkovic, Minlan Yu and Sadia AfrozInternet Measurement Conference (IMC)Oct. 2020
[ paper ][ long slides ][ short slides ] - (IFIP) Enabling Premium Service for Streaming Video in Cellular NetworksXing Xu, Ramesh Govindan, Ajay A Mahimkar, Nemmara K. Shankaranarayanan, Jia Wang and Minlan YuIFIP the International Federation for Information Processing NetworkingJun. 2020
[ paper ] - (TON) Latency equalization as a new network service primitiveMinlan Yu, Marina Thottan and Li LiIEEE/ACM Trasactions on Networking (TON)Feb. 2012
[paper] - (WMUST) Identifying performance bottlenecks in CDNs through TCP-level monitoringPeng Sun, Minlan Yu, Michael J. Freedman and Jennifer RexfordACM SIGCOMM Workshop on Measurements Up the STack (W-MUST)2011
[ paper ][ slides ] - (Presto) Latency Equalization: A Programmable Routing Service PrimitiveMinlan Yu, Marina Thottan and Li LiACM SIGCOMM PRESTO Workshop2008
[ paper ][ slides ]