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:20240214T070310Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231212T140000
DTEND;TZID=Australia/Melbourne:20231212T151500
UID:siggraphasia_SIGGRAPH Asia 2023_sess120@linklings.com
SUMMARY:Character and Rigid Body Control
DESCRIPTION:Technical Papers\n\nAdaptNet: Policy Adaptation for Physics-Ba
 sed Character Control\n\nMotivated by human’s ability to adapt skills in t
 he learning of new ones, this paper presents AdaptNet, an approach for mod
 ifying the latent space of existing policies to allow new behaviors to be 
 quickly learned from like tasks in comparison to learning from scratch. Bu
 ilding on top of a give...\n\n\nPei Xu (Clemson University, Roblox); Kaixi
 ang Xie (McGill University); Sheldon Andrews (École de technologie supérie
 ure, Roblox); Paul G. Kry (McGill University); Michael Neff (University of
  California Davis); Morgan McGuire (Roblox, University of Waterloo); Ioann
 is Karamouzas (University of California Riverside); and Victor Zordan (Rob
 lox, Clemson University)\n---------------------\nC·ASE: Learning Condition
 al Adversarial Skill Embeddings for Physics-based Characters\n\nWe present
  C·ASE, an efficient and effective framework that learns conditional Adver
 sarial Skill Embeddings for physics-based characters. Our physically simul
 ated character can learn a diverse repertoire of skills while providing co
 ntrollability in the form of direct manipulation of the skills to be...\n\
 n\nZhiyang Dou (The University of Hong Kong (HKU)), Xuelin Chen and Qingna
 n Fan (Tencent AI Lab), Taku Komura (University of Hong Kong), and Wenping
  Wang (Texas A&M University)\n---------------------\nViCMA: Visual Control
  of Multibody Animations\n\nMotion control of large-scale, multibody physi
 cs animations with contact is difficult. Existing approaches, such as thos
 e based on optimization, are computationally daunting, and, as the number 
 of interacting objects increases, can fail to find satisfactory solutions.
  We present a new, complementary...\n\n\nDoug L. James (Stanford Universit
 y, NVIDIA) and David I. W. Levin (University of Toronto, NVIDIA)\n--------
 -------------\nNeural Categorical Priors for Physics-Based Character Contr
 ol\n\nRecent advances in learning reusable motion priors have demonstrated
  their effectiveness in generating naturalistic behaviors. In this paper, 
 we propose a new learning framework in this paradigm for controlling physi
 cs-based characters with significantly improved motion quality and diversi
 ty over ex...\n\n\nQingxu Zhu, He Zhang, Mengting Lan, and Lei Han (Tencen
 t)\n---------------------\nMuscleVAE: Model-Based Controllers of Muscle-Ac
 tuated Characters\n\nIn this paper, we present a simulation and control fr
 amework for generating biomechanically plausible motion for muscle-actuate
 d characters. We incorporate a fatigue dynamics model, the 3CC-r model, in
 to the widely-adopted Hill-type muscle model to simulate the development a
 nd recovery of fatigue in...\n\n\nYusen Feng, Xiyan Xu, and Libin Liu (Pek
 ing University)\n---------------------\nDiffFR: Differentiable SPH-based F
 luid-Rigid Coupling for Rigid Body Control\n\nDifferentiable physics simul
 ation has shown its efficacy in inverse design problems. Given the pervasi
 veness of the diverse interactions between fluids and solids in life, a di
 fferentiable simulator for the inverse design of the motion of rigid objec
 ts in two-way fluid-rigid coupling is also demande...\n\n\nZhehao Li and Q
 ingyu Xu (University of Science and Technology of China), Xiaohan Ye and B
 o Ren (Nankai University), and Ligang Liu (University of Science and Techn
 ology of China)\n\nRegistration Category: Full Access\n\nSession Chair: Ju
 ngdam Won (Seoul National University)
END:VEVENT
END:VCALENDAR