BEGIN:VCALENDAR
METHOD:REQUEST
PRODID:Microsoft Exchange Server 2010
VERSION:2.0
BEGIN:VTIMEZONE
TZID:AUS Eastern Standard Time
BEGIN:STANDARD
DTSTART:16010101T030000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=4
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:16010101T020000
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=10
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
ORGANIZER;CN=Australian Centre For Robotics Administration;SENT-BY="mailto:s
 abrina.asri@sydney.edu.au":mailto:acfr.admin@sydney.edu.au
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=everybody:
 mailto:everybody@acfr.usyd.edu.au
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=students@a
 cfr.usyd.edu.au:mailto:students@acfr.usyd.edu.au
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN='academics
 -meeting@acfr.usyd.edu.au':mailto:academics-meeting@acfr.usyd.edu.au
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN=seminars@a
 cfr.usyd.edu.au:mailto:seminars@acfr.usyd.edu.au
ATTACH:CID:image001.png@01DD203F.77942950
DESCRIPTION;LANGUAGE=en-US:Faculty of Engineering\n\n\nACFR Seminar Series\
 n[https://d31hzlhk6di2h5.cloudfront.net/20260730/44/a0/ac/85/83de99ae1318d
 a0add393c81.png]\n[https://d31hzlhk6di2h5.cloudfront.net/20260730/90/62/a1
 /a0/e806283be685b4d065bc82ba.jpg]\nRethinking Efficiency Bottleneck of Gen
 erative AI\n\nPresented by Dr. Zhenghao Chen\nDate: Thursday\, 6 August 20
 26\, at 1:00 pm AEST\nVenue: ACFR seminar area\, J04 level 2 (Rose St Buil
 ding<https://url.au.m.mimecastprotect.com/s/2o5cC6XQ4Lf1BxmvyhDcGf5A01V?do
 main=t.e2ma.net>)\nZoom ID: https://uni-sydney.zoom.us/s/87306457455<https
 ://url.au.m.mimecastprotect.com/s/2yX_C71R2NTQJ9NKZs4fXfodIzG?domain=t.e2m
 a.net>\n\n**RSVP by Tuesday 4 August for catering purposes. Accept this ca
 lendar invitation if you plan to attend the seminar in person and join us 
 for a light lunch at approximately 12.30pm.\n\nAbstract:\n\nGenerative AI 
 has ushered in a new era of breakthroughs across science\, industry\, and 
 society. Yet\, the immense computational\, environmental\, and financial c
 osts required to train and deploy such models pose serious challenges to l
 ong-term sustainability. This talk presents a unified perspective on reduc
 ing these costs by addressing two fundamental bottlenecks: data redundancy
  and model complexity. It introduces two cutting-edge strategies: neural d
 ata compression and generative model compression\, and demonstrates how th
 ey can drastically reduce storage demands\, training overhead\, and infere
 nce latency\, while maintaining or even enhancing model performance. Throu
 gh real-world case studies spanning efficient video\, medical\, and climat
 e data compression\, as well as acceleration techniques for large language
  models\, video generation\, and embodied AI systems\, the talk demonstrat
 es how principled redundancy and complexity reduction can democratize acce
 ss to generative AI. Ultimately\, it argues that sustainable generative AI
  is achievable through efficiency-oriented design\, enabling broader parti
 cipation beyond tech giants and national megaprojects.\n\nBio:\n\n\nDr Zhe
 nghao Chen is a Lecturer (equivalent to Assistant Professor) at the Univer
 sity of Newcastle\, Australia. He received his B.Eng. H1. and Ph.D. from t
 he University of Sydney in 2017 and 2022\, respectively. He worked as as a
  Research Engineer at TikTok\, a Research Fellow at the University of Sydn
 ey\, and a Visiting Research Scientist at Microsoft Research and Disney Re
 search. Dr Chen’s research interests span generative AI\, embodied AI\, 
 AI for science\, and multimedia. He has published 33 papers in CORE A* con
 ferences and JCR Q1 journals\, including flagship conferences such as CVPR
 \, ICCV\, ICML\, ICLR\, ECCV\,  MM\, and AAAI\, as well as leading journal
 s including IEEE Transactions on Image Processing\, IEEE Transactions on P
 attern Analysis and Machine Intelligence\, and IEEE Transactions on Medica
 l Imaging. His research has received more than 2\,800 citations. Dr Chen a
 ctively translates his research into global industrial impact and cross-di
 sciplinary applications. His industrial innovations have resulted in multi
 ple patents and have been deployed in enterprise-scale generative AI syste
 ms worldwide. He also collaborates with scientists to apply AI to major sc
 ientific challenges\, resulting in interdisciplinary publications in Natur
 e Portfolio journals. In recognition of his achievements\, Dr Chen has rec
 eived the Google Australia Prize\, the Australian Government Research Trai
 ning Program International Scholarship\, the ACM SIGMM Outstanding PhD The
 sis Award\, and the Microsoft Research Asia StarTrack Fellowship.\n\n[Regi
 ster for Event >]<https://url.au.m.mimecastprotect.com/s/7OZlC81V0PTzKxq0Y
 sVhkfyWBa-?domain=t.e2ma.net>\n[https://d31hzlhk6di2h5.cloudfront.net/2026
 0730/2e/8d/c7/1c/1c70baef8b350e3840963efe.png]\n\n[Web Site]<https://url.a
 u.m.mimecastprotect.com/s/CZVfC0YKPviMLlB5msJs9f9d-aN?domain=t.e2ma.net>\n
 [LinkedIn]<https://url.au.m.mimecastprotect.com/s/2XSvCgZ0N1im7nyRGF4twf4S
 2Qo?domain=t.e2ma.net>\n[X]<https://url.au.m.mimecastprotect.com/s/XtrJCjZ
 1N7i3vkmXRuOuKfmRQ73?domain=t.e2ma.net>\n[YouTube]<https://url.au.m.mimeca
 stprotect.com/s/qQwgCk81N9trpZBj5C6C5fGNTH4?domain=t.e2ma.net>\n\nCopyrigh
 t © 2026\n\nThe University of Sydney\n\nPlease add acfr.admin@sydney.edu.
 au<mailto:acfr.admin@sydney.edu.au> to your address book or senders safe l
 ist to make sure you continue to see our emails in the future.\n\n\n\nCric
 os Code 00026A  TEQSA PRV12057\nDisclaimer<https://url.au.m.mimecastprotec
 t.com/s/HWEWClx1NjiAvDE8XFAFGfz9dms?domain=t.e2ma.net> | Privacy statement
 <https://url.au.m.mimecastprotect.com/s/GdSyCmO5gluArGl3WFKHBfR9A7v?domain
 =t.e2ma.net> |\n\n\n
UID:040000008200E00074C5B7101A82E00800000000DC4AE4ACEB1FDD01000000000000000
 010000000B45C0F8D8B16F2479DFE7652E7CBF413
SUMMARY;LANGUAGE=en-US:ACFR Seminar Series: Dr. Zhenghao Chen - Rethinking 
 Efficiency Bottleneck of Generative AI
DTSTART;TZID=AUS Eastern Standard Time:20260806T130000
DTEND;TZID=AUS Eastern Standard Time:20260806T140000
CLASS:PUBLIC
PRIORITY:5
DTSTAMP:20260730T062145Z
TRANSP:OPAQUE
STATUS:CONFIRMED
SEQUENCE:0
LOCATION;LANGUAGE=en-US:ACFR J04 Level 2 Seminar Area:\; https://maps.app.g
 oo.gl/PUJdbB9oUTtg5fLr8\; ZOOM:\; https://uni-sydney.zoom.us/s/87306457455
X-MICROSOFT-CDO-APPT-SEQUENCE:0
X-MICROSOFT-CDO-OWNERAPPTID:2124935719
X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE
X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY
X-MICROSOFT-CDO-ALLDAYEVENT:FALSE
X-MICROSOFT-CDO-IMPORTANCE:1
X-MICROSOFT-CDO-INSTTYPE:0
X-MICROSOFT-DONOTFORWARDMEETING:FALSE
X-MICROSOFT-DISALLOW-COUNTER:FALSE
X-MICROSOFT-REQUESTEDATTENDANCEMODE:DEFAULT
X-MICROSOFT-ISRESPONSEREQUESTED:TRUE
X-MICROSOFT-LOCATIONDISPLAYNAME:ACFR J04 Level 2 Seminar Area:\; https://ma
 ps.app.goo.gl/PUJdbB9oUTtg5fLr8\; ZOOM:\; https://uni-sydney.zoom.us/s/873
 06457455
X-MICROSOFT-LOCATIONSOURCE:None
X-MICROSOFT-LOCATIONS:[{"DisplayName":"ACFR J04 Level 2 Seminar Area:"\,"Lo
 cationAnnotation":""\,"LocationUri":""\,"LocationStreet":""\,"LocationCity
 ":""\,"LocationState":""\,"LocationCountry":""\,"LocationPostalCode":""\,"
 LocationFullAddress":""}\,{"DisplayName":"https://maps.app.goo.gl/PUJdbB9o
 UTtg5fLr8"\,"LocationAnnotation":""\,"LocationUri":""\,"LocationStreet":""
 \,"LocationCity":""\,"LocationState":""\,"LocationCountry":""\,"LocationPo
 stalCode":""\,"LocationFullAddress":""}\,{"DisplayName":"ZOOM:"\,"Location
 Annotation":""\,"LocationUri":""\,"LocationStreet":""\,"LocationCity":""\,
 "LocationState":""\,"LocationCountry":""\,"LocationPostalCode":""\,"Locati
 onFullAddress":""}\,{"DisplayName":"https://uni-sydney.zoom.us/s/873064574
 55"\,"LocationAnnotation":""\,"LocationUri":""\,"LocationStreet":""\,"Loca
 tionCity":""\,"LocationState":""\,"LocationCountry":""\,"LocationPostalCod
 e":""\,"LocationFullAddress":""}]
BEGIN:VALARM
DESCRIPTION:REMINDER
TRIGGER;RELATED=START:-PT15M
ACTION:DISPLAY
END:VALARM
END:VEVENT
END:VCALENDAR