Pan Hu

Pan Hu 

Senior Engineer, Alibaba Cloud U.S.
Google Scholar, GitHub
Current Research Interests:
AI for Infra / Infra for AI
Email: lghupan [at] gmail [dot] com
Seeking talented research interns. Contact me if interested!

News

MLSys 
  • Feb. 23 2024: Our comprehensive paper on the CloudEval-YAML benchmark has been accepted by MLSys, a leading conference in machine learning systems. This achievement marks the start of a series of efforts to bring LLM to cloud infra. Stay tuned for more innovations/experiences.
    Code: https://github.com/alibaba/CloudEval-YAML
    Paper: https://arxiv.org/abs/2401.06786

CloudEval 
  • Nov. 15 2023: Exploring the use of Large Language Models (LLMs) for cloud applications? The CloudEval-YAML benchmark could help. It includes practical, hand-curated dataset for cloud-native apps, featuring over 1,000 problems with in-depth evaluations of popular LLMs in cloud settings. Available open-source under Alibaba GitHub at CloudEval-YAML.

VR 
  • Feb. 22, 2022: Announced Alibaba XG beam management system for high density Virtual Reality. The news has been widely covered by over 100 media outlets, highlighting the significance of this technology: 1 2 3. It is recognized as a key component of Alibaba XG Lab's products.

Yunqi 
  • Oct. 20, 2021: Demonstrated drone-based 8K VR streaming with mmWave technology to business and government leaders on the annual Apsara Conference. Our booth was the largest at the event and attracted extensive media coverage: 1 2 3 .

Alibaba 
  • Oct. 26, 2020: I am thrilled to join Alibaba Damo Academy as an Alibaba Star (highest distinction for new grads)!

Selected Papers

Please check Google Scholar for all papers and patents (2000+ citations). [BibTeX]

Conference: SIGCOMM 3, MobiSys 3, MobiCom 2, MLSys 1, SenSys 1, AAAI 1, SOSP 1, NSDI 1
Journal: ACM ToIT 1
Workshop: NeurIPS ML for Systems 1, HotMobile 1

2024

CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation
Yifei Xu1, Yuning Chen1, Xumiao Zhang1, Xianshang Lin, Pan Hu2, Yunfei Ma, Songwu Lu, Wan Du, Z. Morley Mao, Ennan Zhai, Dennis Cai
MLSys 2024 Code Paper

1 Co-first authors. 2 Corresponding author.

2023

CloudEval-YAML: A Realistic and Scalable Benchmark for Cloud Configuration Generation
Yifei Xu1, Yuning Chen1, Xumiao Zhang1, Xianshang Lin, Pan Hu2, Yunfei Ma, Songwu Lu, Wan Du, Z. Morley Mao, Ennan Zhai, Dennis Cai
NeurIPS 2023 Workshop on ML for Systems Code Paper

1 Co-first authors. 2 Corresponding author.

2020

Starfish: Resilient Image Compression for AIoT Cameras
Pan Hu, Junha Im, Zain Asgar, Sachin Katti
SenSys 2020 Talk Code

Continuous Measurement of Interactions with the Physical World with a Wrist-Worn Backscatter Reader
Ali Kiaghadi, Pan Hu, Jeremy Gummeson, Soha Rostaminia, Deepak Ganesan
ACM Transactions on Internet of Things

2019

Dejavu: Enhancing Videoconferencing with Prior Knowledge
Pan Hu, Rakesh Misra, Sachin Katti
HotMobile 2019 Talk Poster

2018

Cellular Network Traffic Scheduling with Deep Reinforcement Learning
Sandeep Chinchali, Pan Hu, Tianshu Chu, Manu Sharma, Manu Bansal, Rakesh Misra, Marco Pavone, Sachin Katti
AAAI 2018

2016

Braidio: An Integrated Active-Passive Radio for Mobile Devices with Asymmetric Energy Budgets
Pan Hu, Pengyu Zhang, Mohammad Rostami, Deepak Ganesan
SIGCOMM 2016 Talk

Enabling Practical Backscatter Communication for On-body Sensors
Pengyu Zhang, Mohammad Rostami, Pan Hu, Deepak Ganesan
SIGCOMM 2016

2015

Software Defined Batteries
Anirudh Badam, Ranveer Chandra, Jon A. Dutra, Anthony Ferrese, Steve Hodges, Pan Hu, Julia Meinershagen, Thomas Moscibroda, Bodhi Priyantha, Evangelia Skiani
SOSP 2015 Talk
Authors ranked alphabetically.

CIDER: Enabling Robustness-Power Tradeoffs on a Computational Eyeglass
Addison Mayberry, Yamin Tun, Pan Hu, Duncan Smith-Freedman, Deepak Ganesan, Benjamin Marlin, Christopher Salthouse
MobiCom 2015

Laissez-Faire: Fully asymmetric backscatter communication
Pan Hu, Pengyu Zhang, Deepak Ganesan
SIGCOMM 2015 Talk

2014

EkhoNet: High Speed Ultra Low-Power Backscatter
Pengyu Zhang, Pan Hu, Vijay Pasikanti, Deepak Ganesan
MobiCom 2014 (Best Paper Award Runner Up)

iShadow: Design of a Wearable, Real-Time Mobile Gaze Tracker
Addison Mayberry, Pan Hu, Benjamin Marlin, Christopher Salthouse and Deepak Ganesan
MobiSys 2014

Epsilon: A Visible Light Based Positioning System
Liqun Li, Pan Hu, Guobin Shen, Chunyi Peng, Feng Zhao
NSDI 2014

2013

ViRi: View it Right
Pan Hu, Guobin Shen, Liqun Li, Donghuan Lu
MobiSys 2013

Auditeur: A Mobile-Cloud Service Platform for Acoustic Event Detection on Smartphones
Shahriar Nirjon, Robert Dickerson, Philip Asare, Qiang Li, Dezhi Hong, John Stankovic, Pan Hu, Guobin Shen, and Xiaofan Jiang
MobiSys 2013

Education and Research Experience

Stanford 

Ph.D. in Electrical Engineering, Stanford University
Sep. 2016 - 2021
Advisor: Sachin Katti

Alibaba 

Research Intern, Alibaba US
Jun. 2019 - Sep. 2019

Uhana 

Data Science Intern, Uhana
Jun. 2018 - Sep. 2018
Jun. 2017 - Sep. 2017

UMass 

M.S. in Computer Science, UMass Amherst
Sep. 2013 - May. 2016
Advisor: Deepak Ganesan

MSR 

Mobility and Networking Research Group , Microsoft Research Redmond
Jun. 2014 - Sep. 2014

MSRA 

Mobile and Sensing System Group, Microsoft Research Asia
Jun. 2012 - Jun. 2013

Whut 

B.S. In Electronic Information Engineering
Sep. 2008 - Jun. 2012
Wuhan University of Technology, Wuhan, Hubei Province, P.R.C.

Awards

  • Microsoft PhD Fellowship, 2015

  • Best paper Award Runner-up, MobiCom 2014

Services

  • Technical Program Committee: MobiCom’24

  • Reviewer / external reviewer: IEEE Transaction on Mobile Computing, IEEE Journal on Selected Areas in Communications, IEEE Signal Processing Magazine, Optics Express, Wireless Communications and Mobile Computing , SIGCHI’15, Ubicomp’16

  • Web chair: HotWireless’14