• 02/27/2023: 😁 I received the tenure decision letter! I will be promoted to Associate Professor and awarded tenure effectively July 1, 2023.
• 01/28/2023: [Paper] Two papers have been accepted to CCGrid 2023. It is great to see LayerCake, the last piece of Sam's thesis got accepted! The other paper on gradient accumulation is conditionally accepted. [Update:02/27/2023] The revision is successful and the revised submission has been accepted!
• 01/13/2023: 💰 [Grant] I received the NSF CAREER award to work on designing a specialized edge for AR.
• 12/09/2022: [Paper] Our paper on dual-camera lighting estimation for virtual try-on applications has been accepted to HotMobile 2023!
• 10/26/2022: [Talk] I gave a keynote speech at Mass Academy of Math and Science during the Conversations about STEM 2022 event, about my research on cloud-based distributed training and edge support for mobile AR and personal experience in grant writings and in STEM.
• 10/04/2022: [Paper] Our paper Funcpipe has been accepted to SIGMETRICS' 23!
• 09/27/2022: [Talk] I gave a keynote speech at the 2nd International Workshop on Testing Distributed Internet of Things Systems(TDIS’22), titled "Experiences with cloud-based distributed training and edge support for mobile AR".
• 06/29/2022: 🥳 My second Ph.D. student Sam Ogden has successfully defended his thesis on "MiseEnPlace: Fine- and Coarse-grained Approaches for Mobile-Oriented Deep Learning"! Dr. Ogden has joined California State Monterey bay as an tenure-track Assistant Professor, congrats!
• 04/08/2022: [Award] I am honored to receive the 2022 award for Outstanding Achievement by a Young Alum from The Manning College of Information and Computer Sciences, UMass Amherst.
• 01/13/2022: 🥳 My first Ph.D. student Xin Dai (co-advised with Prof. Kong) has successfully defended his thesis on "Redesigning Deep Neural Networks for Resource-Efficient Inference"! Dr. Dai has joined Visa Research, congrats!
• 09/22/2021: [Talk] I gave an invited talk on speeding up cloud-based distributed training in the Xia Peisu Forum. I was glad to see a good attendance and enjoyed great talks by other researchers on various topics! Maybe all-things-graphs are the future?
• 08/27/2021: [Paper] Our vision paper on decarbonizing the cloud has been accepted to SoCC 2021! This is a collaboration between UMass Amherst and Caltech.
• 08/25/2021: [Teach] Our academic year officially starts and I am both excited and nervous about going back in-person; well, it has been a while since mid March 2019. I hope I don't disappoint!
• 08/07/2021: [Paper] The shepherding process of DELI was successful and DELI has been officially accepted to IC2E 2021. Meanwhile, the organizing committee of IC2E is finalizing our position paper on the future of cloud engineering! Oh and FishNet, our first attempt to toward resource-efficient multi-task learning, has been accepted to CIKM 2021! We think that FishNet has the potential of modernizing mobile AR.
• 06/29/2021: [Paper] Fidelius has been accepted to IC2E 2021 and DELI has been conditionally accepted! These two projects are both related to speeding up deep learning, the former is for inference while the later is for training.
• 05/23/2021: 🔥 [Paper] I am happy to announce that our paper Xihe has been accepted to MobiSys 2021! Xihe is a 3D Vision-based Lighting Estimation Framework for Mobile Augmented Reality; it provides fast (~20ms per estimation) and accurate lighting estimation compared to ARKit and GLEAM.
• 05/10/2021: 🔥 [Paper] Our paper Few-shot NAS has been accepted to ICML as a long oral! Our few-shot NAS improves the accuracy of architecture evaluation with a small increase of evaluation cost compared to one-shot NAS!
• 04/30/2021: 🔥 [Paper] After 1.5 years investigation with great efforts from JB and a number of other students, we have an update for our findings on secure deep inference with TEEs. Check out our arXiv paper!
• 04/28/2021: 💰 [Grant] Thanks to NSF/VMWare for funding our CarbonFirst project! This is a collaborative project led by UMass Amherst. More on this article.
• 03/17/2021: 🔥 [Paper] Our paper Sync-switch has been accepted to ICDCS'21! Sync-switch is a hybrid synchronization approach for distributed deep learning. It combines the benefits of both BSP and ASP, i.e., reducing training time while simultaneously maintaining the converged accuracy.
• 01/25/2021: 🔥 [Paper] Our paper on improving cloud-based inference performance has been accepted to ICPE 2021. PieSlicer dynamically decides where to preprocess the inference input to trade-off on-device processing time and network time. Congrats to my Ph.D. student Sam! Fun facts: you thought we are joking about the Cake Lab? Also, about my dog, can you find her?
• 12/21/2020: 🔥 [Paper] Our paper on mobile-cloud collaborative inference has been accepted to SDM 2021. We redesigned CiNet from the outset to consider the low on-device computation and network transmission cost! Congrats to Xin, co-advised with Prof. Xiangnan Kong! Fun fact: my cat made his debut in this paper! Spoiler alert: my dog will make her debut soon. Stay tuned 😃
• 07/25/2020: [Papers] Two papers have been accepted to ACM Multimedia 2020. Congrats to all collaborators! GRAD is a new ABR algorithm that is tailored for Scalable Video Coding (SVC) and VVSec investigates the use of adversarial perturbation in volumetric video streaming.
• 07/20/2020: [Paper] Our paper on understanding the performance implication of concurrent kernels placement policies has been accepted to Perf'20! Hearty congrats to the student lead Guin and to all other authors! This is Guin's first conference paper since her started Ph.D. program at WPI.
• 07/17/2020: [Paper] Our paper EPNet on dynamic inference execution has been accepted to CIKM'20! Congrats to Xin, co-advised with Prof. Xiangnan Kong!
• 07/02/2020: [Paper] Our paper PointAR on Mobile AR-oriented lighting estimation has been accepted to ECCV'20! Congrats to my student Yiqin!
• 06/12/2020: 👏🏼👏🏼👏🏼 [Award] Our paper QuRate on efficient VR power has received the best paper award and the DASH-IF Excellence in DASH Award (3rd place) at MMSys'20! Congrats to all collaborators.
• 05/16/2020: [Paper] Our paper on guided multi-attention classification has been accepted to KDD'20!
• 03/16/2020: [Paper] Our QuRate paper on VR power has been accepted to MMSys'20. This was a collaboration with Rutgers, UNL, SUNY Binghamton, SUNY Buffalo and Adobe Research.
• 03/13/2020: [Papers] Two papers, CM-DARE and DistStream, have been accepted to ICDCS'20! DistStream was a collaboration with ISCA.
• 03/03/2020: I attended the HotMobile'20 in Austin, Texas where our poster PointAR was accepted.
• 02/07/2020: [Papers] Two papers MDInference and Perseus have been accepted to IC2E'20.
• 01/06/2020: I will be serving on the PC for ICDCS'20 Edge computing track. ICDCS'20 will be held in Singapore.
• 11/04/2019: I will be serving on the PC for HPDC'20 which will be held in Sweden.
• 10/11/2019: I will be serving on the PC for ACSOS'20, please consider submitting! ACSOS is a new conference founded as a merger of ICAC and SASO.
• 02/28/2019: Check out our distributed deep learning paper here.
• 12/17/2018: Our paper on GC inefficiency for big data applications has been accepted at VLDB'19. This was a collaboration with ISCAS.
• 10/31/2018: I will be serving as the Publicity Vice Chair for ICAC 2019 and SASO 2019, please consider submitting!
• 09/25/2018: I was selected and supported as one of the Faculty Scholars to attend 2018 Grace Hopper Annual Conference in Houston, Texas.
• 08/13/2018: I will be serving on CCGRID'19 Architecture and Networking track PC, please consider submitting!
• 07/14/2018: I will be serving on IoTDI'19 PC, please consider submitting!
• 06/25/2018: 💰 [Grant] Thanks to National Science Foundation for funding my project on efficient mobile deep inference!
• 04/30/2018: 🔥 My student Sam Ogden and I had our paper on efficient mobile deep inference accepted at HotEdge 2018!
• 03/19/2018: I will be serving on InfoComm'19 PC, please consider submitting!
• 03/06/2018: 💰 [Grant] Thanks to National Science Foundation for funding my project on mobile-aware resource management!
• 12/07/2017: 🔥 My mobile deep inference paper has been accepted for publishing in IC2E'18!
• 11/25/2017: 🔥 Our geo-elasticity paper has been accepted for publishing in TOIT'17.
• 07/29/2017: 🔥 Our paper on cloud-based SDN measurement has been accepted for publishing in IEEE NFV-SDN'17. This is a collaboration with Craig Shue.
• More news on the way...