Skip to Content.
Sympa Menu

inf-seminars - Re: [research-staff] Talk Oct 6: Accelerating Deep Learning Models, from Industry to Academia

Subject: Seminars relevant to Informatics

List archive

Chronological Thread  
  • From: Luo Mai <luo.mai AT ed.ac.uk>
  • To: Le Xu <le.xu AT ed.ac.uk>, "research-students AT inf.ed.ac.uk" <research-students AT inf.ed.ac.uk>, "research-staff AT inf.ed.ac.uk" <research-staff AT inf.ed.ac.uk>, "inf-seminars AT mlist.is.ed.ac.uk" <inf-seminars AT mlist.is.ed.ac.uk>
  • Subject: Re: [research-staff] Talk Oct 6: Accelerating Deep Learning Models, from Industry to Academia
  • Date: Tue, 6 Oct 2026 12:54:15 +0000

Hi All,

The talk actually will start at 2pm today (in 10 minutes!). Sorry for the wrong time in the previous email.

Please drop by 3.07 (IMR) Informatics Forum or join us on Teams.

Thanks.

Best,
Luo
 
---------------------------------------------------------------
Luo Mai
Associate Professor
School of Informatics, University of Edinburgh
Homepage: https://luomai.github.io
Office: IF-2.03, Informatics Forum, EH8 9AB
---------------------------------------------------------------

From: research-staff <research-staff-bounces AT inf.ed.ac.uk> on behalf of Le Xu <le.xu AT ed.ac.uk>
Date: Sunday, October 4, 2026 at 10:13 PM
To: research-students AT inf.ed.ac.uk <research-students AT inf.ed.ac.uk>; research-staff AT inf.ed.ac.uk <research-staff AT inf.ed.ac.uk>; inf-seminars AT mlist.is.ed.ac.uk <inf-seminars AT mlist.is.ed.ac.uk>
Subject: Re: [research-staff] Talk Oct 6: Accelerating Deep Learning Models, from Industry to Academia

This talk (15:00 Oct 6th) will also be available remotely on teams (see below).

See you then!

Le

----------

Microsoft Teams meeting
Meeting ID: 347 857 880 826 358 1
Passcode: xS7qt67J
----------


Le Xu
University of Edinburgh

From: research-staff <research-staff-bounces AT inf.ed.ac.uk> on behalf of Le Xu <le.xu AT ed.ac.uk>
Sent: 04 October 2026 21:49
To: research-students AT inf.ed.ac.uk <research-students AT inf.ed.ac.uk>; research-staff AT inf.ed.ac.uk <research-staff AT inf.ed.ac.uk>; inf-seminars AT mlist.is.ed.ac.uk <inf-seminars AT mlist.is.ed.ac.uk>
Subject: [research-staff] Talk Oct 6: Accelerating Deep Learning Models, from Industry to Academia
 
Dear all -- 

Dr. Guosheng Hu from the University of Bristol will be visiting us this coming Tuesday (Oct. 6). He will be giving a talk from 15:00 to 16:00 (see details below). He will be around all day Tuesday. If you're interested in speaking with him, you can reach him at g.hu AT bristol.ac.uk.
See you then!
Le


--------

When: Tuesday October 6, 15:00 to 16:00

Where: 3.07 (IMR) Informatics Forum
Title: Accelerating Deep Learning Models, from Industry to Academia
Abstract: AI-driven data centres, operating continuously and predominantly powered by fossil fuels, contribute significantly to global greenhouse gas emissions (2.5-3.7%). The widespread use of large foundation models such as ChatGPT exacerbates this environmental impact. This talk explores strategies for mitigating AI's carbon footprint through model acceleration, aiming to significantly reduce computations while maintaining the accurate of AI models. This session will spotlight various model acceleration techniques, including Model Quantisation, Model Pruning, Neural Architecture Search and others. Apart from academic publications, the industry practice will also be introduced.
Bio: Dr. Guosheng Hu is a senior lecturer of AI at the University of Bristol. Before that, he served as the Head of Research at Oosto (a leading visual AI company). Prior to his role at Oosto, he was a Research Fellow in the LEAR team at INRIA Grenoble Rhone-Alpes, France. Dr. Hu earned his PhD under the supervision of Prof. Josef Kittler at the University of Surrey, UK.
-------- 



Le Xu
University of Edinburgh
The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. Is e buidheann carthannais a th’ ann an Oilthigh Dhùn Èideann, clàraichte an Alba, àireamh clàraidh SC005336.


Archive powered by MHonArc 2.6.24.

Top of Page