BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190158Z
LOCATION:West Building\, Rooms 211-214
DTSTART;TZID=America/Los_Angeles:20250813T092000
DTEND;TZID=America/Los_Angeles:20250813T093000
UID:siggraph_SIGGRAPH 2025_sess128_papers_454@linklings.com
SUMMARY:RELATE3D: REfocusing Latent Adapter for Targeted local Enhancement
  and Editing in 3D Generation
DESCRIPTION:Xiao-Lei Li (Tsinghua University, Tencent Video AI Center); Ha
 o-Xiang Chen (Tsinghua University); Yanni Zhang (Tencent Video AI Center);
  Kai Ma (Tencent PCG); Alan Zhao (Tencent Video AI Center); Tai-Jiang Mu (
 Tsinghua University); Haoxiang Guo (Skywork AI, Kunlun Inc.); and Ran Zhan
 g (Tencent Video AI Center)\n\nThe alignment of text,images,and 3D is very
  challenging,yet it is crucial and beneficial for many tasks.We explore an
 d reveal the characteristics of the native 3D latent space for 3D generati
 on,make it decomposable and low-rank,thereby enabling efficient learning f
 or multimodal local alignment,achieving precise local enhancement and part
 -level editing of 3D geometry.\n\nInterest Area: Research & Education\n\nR
 ecording: Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nRegist
 ration Category: Full Conference, Virtual Access, Wednesday\n\nSession Cha
 ir: Yael Vinker (Massachusetts Institute of Technology (MIT), MIT CSAIL)\n
 \n
END:VEVENT
END:VCALENDAR