
Stylianos I. Venieris
@sivenieris
Senior Research Scientist / Head of Distributed AI group at Samsung AI, Cambridge, UK
ID: 1270706519689084930
https://steliosven10.github.io/ 10-06-2020 13:17:06
130 Tweet
210 Followers
159 Following

Checkout out our Fluid Batching work, accepted at IEEE/ACM ICCAD! We designed a SOTA flexible batching method for NPU-based inference serving, showcasing how rethinking ML system design for upcoming use-cases can lead to combined high throughput and low tail latency. Samsung Research


This Wednesday (Nov 1st), Stylianos I. Venieris will be presenting our work on "Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs" at #ICCAD2023. Tune in for more ... Preprint: arxiv.org/abs/2209.13443 Co-authored-by: Alexandros Kouris , nic lane


Our paper presenting Fluid Batching has been selected as Best Paper Award Finalist at IEEE/ACM ICCAD 2023! If you find yourself in SF, come by my talk and poster on Wednesday to know more. Preprint: arxiv.org/abs/2209.13443 Samsung Research

From SpatialML industrial advisor Stylianos I. Venieris and coauthors!

We are very excited to release the list of accepted papers for this year's DistributedML workshop, along with a tentative schedule here: distributedml.org/program/ Looking forward to seeing you in Paris, ACM SIGCOMM #CoNEXT23.


Great talk Young D. Kwon -- continual learning on your phone 😎 ACM SenSys; work w/ Hong Jia, Stylianos I. Venieris, Jagmohan Chauhan, Cecilia Mascolo🇪🇺🇬🇧


Our GenAI group at Samsung Electronics AI in Cambridge, UK has open positions for ML Engineers. Check out more info and application details: linkedin.com/posts/styliano… Join us!

Thanks to Blaize, Lumai, Samsung Electronics and Sally Ward-Foxton from EE Times | Electronic Engineering Times for a brilliant panel earlier today on next-generation hardware and system design for #EdgeAI at the AI Infra Connect (Formerly AI Hardware and Systems #AIHWEdgeAISummit in London.




What are we going to do now that trends in model size (LLM and FMs) are breaking our ability to put them on-device? One answer is in the keynote from Stylianos I. Venieris MobiUK 2024 pitching the Consumer Edge 2.0 vision. Details in: arxiv.org/abs/2210.10514 to appear in Pervasive Computing


Find me and Young D. Kwon presenting our work TinyTrain at #ICML2024 Poster Session II at 1:30-3pm Vienna time Link to paper in ICML proceedings: proceedings.mlr.press/v235/kwon24c.h… Great work led by Young D. Kwon 🚀and kudos to our co-authors Stylianos I. Venieris Jagmohan Chauhan nic lane Cecilia Mascolo🇪🇺🇬🇧


TinyTrain allows *learning* not just inference to be performed on MCUs in a compute-, memory- and data-efficient manner! Young and other co-authors are at #ICML2024, reach out to chat. TinyTrain work by Young D. Kwon, Rui Li, Stylianos I. Venieris, Jagmohan Chauhan, nic lane and Cecilia Mascolo🇪🇺🇬🇧

With Christos Kyrkou, we are excited to chair a new topic "A6 Applications of Artificial Intelligence Systems" at DATE Conference 2025.! Details: date-conference.com/tpc#A6 Abstract deadline: Sept 15 2024 Paper deadline: Sept 22 2024 Submission site: softconf.com/date25/confere…
