BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070311Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T140000
DTEND;TZID=Australia/Melbourne:20231214T150000
UID:siggraphasia_SIGGRAPH Asia 2023_sess132@linklings.com
SUMMARY:Personalized Generative Models
DESCRIPTION:Technical Papers\n\nDomain-Agnostic Tuning-Encoder for Fast Pe
 rsonalization of Text-To-Image Models\n\nText-to-image (T2I) personalizati
 on allows users to guide the creative image generation process by combinin
 g their own visual concepts in natural language prompts. \nRecently, encod
 er-based techniques have emerged as a new effective approach for T2I perso
 nalization, reducing the need for multiple ima...\n\n\nMoab Arar (Tel-Aviv
  University); Rinon Gal (Tel Aviv University, NVIDIA Research); Yuval Atzm
 on (NVIDIA Research); Gal Chechik (NVIDIA Research, Bar-Ilan University); 
 Daniel Cohen-Or (Tel Aviv University); Ariel Shamir (Reichman University (
 IDC)); and Amit H. Bermano (Tel Aviv University)\n---------------------\nP
 roSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion 
 Models\n\nPersonalizing generative models offers a way to guide image gene
 ration with user-provided references. Current personalization methods can 
 invert an object or concept into the textual conditioning space and compos
 e new natural sentences for text-to-image diffusion models. However, repre
 senting and ed...\n\n\nYuxin Zhang (MAIS, Institute of Automation, Chinese
  Academy of Sciences; School of Artificial Intelligence, University of Chi
 nese Academy of Sciences); Weiming Dong (MAIS, Institute of Automation, Ch
 inese Academy of Sciences; School of AI,University of Chinese Academy of S
 ciences); Fan Tang (Institute of Computing Technology, Chinese Academy of 
 Sciences); Nisha Huang (School of AI,University of Chinese Academy of Scie
 nces; MAIS, Institute of Automation, Chinese Academy of Sciences); Haibin 
 Huang and Chongyang Ma (Kuaishou Technology); Tong-Yee Lee (National Cheng
 -Kung University); Oliver Deussen (University of Konstanz); and Changsheng
  Xu (MAIS, Institute of Automation, Chinese Academy of Sciences; School of
  Artificial Intelligence, University of Chinese Academy of Sciences)\n----
 -----------------\nContent-based Search for Deep Generative Models\n\nThe 
 growing proliferation of customized and pretrained generative models has m
 ade it infeasible for a user to be fully cognizant of every model in exist
 ence. To address this need, we introduce the task of content-based model s
 earch: given a query and a large set of generative models, finding the mod
 ...\n\n\nDaohan Lu, Sheng-Yu Wang, Nupur Kumari, Rohan Agarwal, and Mia Ta
 ng (Carnegie Mellon University); David Bau (Northeastern University); and 
 Jun-Yan Zhu (Carnegie Mellon University)\n---------------------\nA Neural 
 Space-Time Representation for Text-to-Image Personalization\n\nA key aspec
 t of text-to-image personalization methods is the manner in which the targ
 et concept is represented within the generative process. This choice great
 ly affects the visual fidelity, downstream editability, and disk space nee
 ded to store the learned concept. In this paper, we explore a new t...\n\n
 \nYuval Alaluf, Elad Richardson, Gal Metzer, and Daniel Cohen-Or (Tel Aviv
  University)\n---------------------\nMyStyle++: A Controllable Personalize
 d Generative Prior\n\nIn this paper, we propose an approach to obtain a pe
 rsonalized generative prior with explicit control over a set of attributes
 . We build upon MyStyle, a recently introduced method, that tunes the weig
 hts of a pre-trained StyleGAN face generator on a few images of an individ
 ual. This system allows sy...\n\n\nLibing Zeng (Texas A&M University), Lel
 e Chen and Yi Xu (OPPO US Research Center), and Nima Kalantari (Texas A&M 
 University)\n\nRegistration Category: Full Access\n\nSession Chair: Jun-Ya
 n Zhu (Carnegie Mellon University)
END:VEVENT
END:VCALENDAR