I currently work at Microsoft Research (MSR), Bengaluru, India. I'd my Ph.D. in Computer Science, advised by Prof. Junehwa Song at the NClab in KAIST. I have interned at Microsoft Research, Asia (MSRA) - System Group from June 2015 to Dec. 2015, mentored by Dr. Yunxin Liu (now Professor at Tsinghua University).

Selected Publications

[IMWUT'23/UbiComp'23] HyWay: Enabling Mingling in the Hybrid World
Harsh Vijay, Saumay Pushp, , Amish Mittal, Praveen Gupta, Sirish Gambhira, Shivang Chopra, Mayank Baranwal, Arshia Arya, Ajay Manchepalli, and Venkata N. Padmanabhan.
To appear in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Vol. 7, No. 2, Article 77 (33 pages).
  -- This work was mentioned by Satya Nadella in his (India) Town Hall, January, 2023.

[TMC'20] DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning
Mengwei Xu, Feng Qian, Mengze Zhu, Feifan Huang, Saumay Pushp, and Xuanzhe Liu.
In IEEE Transactions on Mobile Computing, Vol. 19, No. 2, pp. 314-330, Feb. 2020.


[MobiCom'19] Occlumency: Privacy-preserving Remote Deep-learning Inference Using SGX.
Taegyeong Lee, Zhiqi Lin, Saumay Pushp, Caihua Li, Yunxin Liu, Youngki Lee, Fengyuan Xu, Chenren Xu, Lintao Zhang, and Junehwa Song.
In Proceedings of the 25th Annual International Conference on Mobile Computing and Networking. Acceptance rate = 16% (30/186).
[presentation video]


[IMWUT'18/UbiComp'18] PrivacyShield: A Mobile System for Supporting Subtle Just-in-time Privacy Provisioning through Off-Screen-based Touch Gestures.
Saumay Pushp, Yunxin Liu, Mengwei Xu, Changyoung Koh, and Junehwa Song.
In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2, 2 (June 2018), Article 76 (38 pages). Acceptance rate = 22%, February 2018 cycle.

[MobiCom'17] RAVEN : Perception-aware Optimization of Power Consumption for Mobile Games
Saumay Pushp, Chanyou Hwang (co-first authors), Changyoung Koh, Jungpil Yoon, Yunxin Liu, Seungpyo Choi, and Junehwa Song.
In Proceedings of the 23rd International Conference on Mobile Computing and Networking. Acceptance rate = 19% (35/186).
  -- This work was featured and introduced in Microsoft Research Blog [Link]

[TMC'17] ShuffleDog: Characterizing and Adapting User-Perceived Latency of Android Apps
Gang Huang, Mengwei Xu, Felix Xiaozhu Lin (co-first authors), Yunxin Liu, Yun Ma, Saumay Pushp, and Xuanzhe Liu.
In IEEE Transactions on Mobile Computing, Vol. 16, No. 10, pp. 2913-2926, Oct. 2017.

Full Publication list

Reviewing Activities

(External) Reviewer
IMWUT/UbiComp, WWW, ASONAM, IEEE Wireless Communications Magazine, IEEE Transactions on Neural Networks and Learning Systems, etc.

Invited Talks/Presentations

RAVEN : Perception-aware Optimization of Power Consumption for Mobile Games @ IBM Research-Austin; Qualcomm-San Diego; Microsoft Research-Redmond; October, 2017.

Honors and Awards

• Excellence Award from Microsoft Research Lab - Asia (Given to Top ~14% interns in MSRA)
• KAIST Scholarship for Graduate Study (from 2011-2017)
• Winner of the Grant Award (Venture Research Program for Graduate and Ph.D. Students - KAIST Fall Semester 2015, and KAIST Spring Semester 2018)