BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212948Z
LOCATION:Mile High 4
DTSTART;TZID=America/Denver:20240801T140000
DTEND;TZID=America/Denver:20240801T153000
UID:siggraph_SIGGRAPH 2024_sess143@linklings.com
SUMMARY:Character Control
DESCRIPTION:Strategy and Skill Learning for Physics-based Table Tennis Ani
 mation\n\nWe present a strategy and skill learning approach for physics-ba
 sed table tennis animation. We demonstrate a hierarchical control system f
 or diversified skill learning and a strategy learning framework for effect
 ive decision-making. Our strategy learning framework is validated through 
 both agent-age...\n\n\nJiashun Wang (Carnegie Mellon University); Jungdam 
 Won (Seoul National University); and Jessica Hodgins (Carnegie Mellon Univ
 ersity, The AI Institute)\n---------------------\nInteractive Character Co
 ntrol With Auto-regressive Motion Diffusion Models\n\nWe present A-MDM, an
  auto-regressive diffusion model for kinematic motion synthesis. A-MDM can
  be effectively trained with large motion datasets to synthesize high-qual
 ity and diverse motions. Once trained, A-MDM can be combined with various 
 control methods to generate motions for new downstream tas...\n\n\nYi Shi 
 (Simon Fraser University, Shanghai Aritificial Intelligence Laboratory); J
 ingbo Wang and Xuekun Jiang (Shanghai Aritificial Intelligence Laboratory)
 ; Bingkun Lin (Xmov); Bo Dai (Shanghai Aritificial Intelligence Laboratory
 ); and Xue Bin Peng (Simon Fraser University, NVIDIA)\n-------------------
 --\nCharacter Control - Interactive Discussion\n\nAfter the summary presen
 tations, attendees will participate in an interactive discussion. Distribu
 ted around the room will be a series of poster boards for authors to gathe
 r around with the audience. Authors are invited to bring any material rela
 ted to their paper that could instigate further conver...\n\n-------------
 --------\nSuperPADL: Scaling Language-directed Physics-based Control With 
 Progressive Supervised Distillation\n\nWe present a framework for scaling 
 physics-based text-to-motion models to datasets containing thousands of mo
 tions. Our approach being with using reinforcement learning to train a lar
 ge number of expert tracking policies. We then progressively distill these
  experts into larger, more capable networks...\n\n\nJordan B. Juravsky (NV
 IDIA, Stanford University); Yunrong Guo (NVIDIA); Sanja Fidler (NVIDIA, Un
 iversity of Toronto); and Xue Bin Peng (NVIDIA, Simon Fraser University)\n
 ---------------------\nCategorical Codebook Matching for Embodied Characte
 r Controllers\n\nThis work presents a generative VQ framework to translate
  movements of a real user onto a virtual embodied avatar using VR inputs. 
 Our proposed codebook matching technique enables simultaneously learning a
 nd sampling the motions in form of Categorical probabilities and produces 
 realistic full-body m...\n\n\nSebastian Starke and Paul Starke (Facebook R
 eality Labs), Taku Komura (University of Hong Kong), and Yuting Ye (Facebo
 ok Reality Labs)\n---------------------\nMoConVQ: Unified Physics-based Mo
 tion Control via Scalable Discrete Representations\n\nWe present MoConVQ, 
 a uniform framework enabling simulated avatars to acquire diverse skills f
 rom large, unstructured datasets. Leveraging a rich and scalable discrete 
 skill representation, MoConVQ supports a broad range of applications, incl
 uding pose estimation, interactive control, text-to-motion...\n\n\nHeyuan 
 Yao and Zhenhua Song (School of Computer Science, Peking University); Yuya
 ng Zhou (Peking University, School of EECS); Tenglong Ao (School of Comput
 er Science, Peking University); and Baoquan Chen and Libin Liu (Peking Uni
 versity, State Key Laboratory of General Artificial Intelligence)\n-------
 --------------\nLearning Physically Realizable Skills for Online Packing o
 f General 3D Shapes\n\nWe study the problem of learning online packing ski
 lls for irregular 3D shapes. The goal is to consecutively move a sequence 
 of 3D objects with arbitrary shapes into a designated container with only 
 partial sequence observations. Our approach considers physical realizabili
 ty, involving physics dynam...\n\n\nHang Zhao (School of Computer Science 
 National University of Defense Technology), Zherong Pan (Tencent - Lightsp
 eed Studio), Yang Yu (National Key Laboratory for Novel Software Technolog
 y), Kai Xu (School of Computer Science National University of Defense Tech
 nology), and Hang Zhao\n\nInterest Area: Research & Education\n\nKeyword: 
 Animation\n\nRegistration Category: Full Conference, Full Conference Suppo
 rter, Virtual Access, Exhibitor Full Conference, Thursday\n\nSession Chair
 : Teseo Schneider (University of Victoria)
END:VEVENT
END:VCALENDAR