A
Andrei Kulik
Researcher at Google
Publications - 5
Citations - 413
Andrei Kulik is an academic researcher from Google. The author has contributed to research in topics: Android (operating system) & Mobile device. The author has an hindex of 4, co-authored 4 publications receiving 284 citations.
Papers
More filters
Proceedings ArticleDOI
AI Benchmark: All About Deep Learning on Smartphones in 2019
Andrey Ignatov,Radu Timofte,Andrei Kulik,Seung-Soo Yang,Ke Wang,Felix Baum,Max Wu,Lirong Xu,Luc Van Gool +8 more
TL;DR: In this article, the authors evaluate the performance and compare the results of all chipsets from Qualcomm, HiSilicon, Samsung, MediaTek and Unisoc that are providing hardware acceleration for AI inference.
Patent
Storing encrypted objects
TL;DR: In this article, an encrypted resource is stored in association with an access control list, and a request to retrieve the resource is received, and the wrapped key and the authentication credentials are sent, from the application server system, to a key server system.
Posted Content
AI Benchmark: All About Deep Learning on Smartphones in 2019
Andrey Ignatov,Radu Timofte,Andrei Kulik,Seung-Soo Yang,Ke Wang,Felix Baum,Max Wu,Lirong Xu,Luc Van Gool +8 more
TL;DR: This paper evaluates the performance and compares the results of all chipsets from Qualcomm, HiSilicon, Samsung, MediaTek and Unisoc that are providing hardware acceleration for AI inference and discusses the recent changes in the Android ML pipeline.
Posted Content
On-Device Neural Net Inference with Mobile GPUs
Juhyun Lee,Nikolay Chirkov,Ekaterina Ignasheva,Yury Pisarchyk,Mogan Shieh,Fabio Riccardi,Raman Sarokin,Andrei Kulik,Matthias Grundmann +8 more
TL;DR: This paper presents how the mobile GPU is leverage, a ubiquitous hardware accelerator on virtually every phone, to run inference of deep neural networks in real-time for both Android and iOS devices and discusses how to design networks that are mobile GPU-friendly.
Journal ArticleDOI
Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations
TL;DR: In this article , the authors present a series of implementation optimizations for large diffusion models that achieve the fastest reported inference latency to-date (under 12 seconds for Stable Diffusion 1.4 without int8 quantization on Samsung S23 Ultra for a 512x512 image with 20 iterations).