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:20260417T190052Z
LOCATION:West Building\, Rooms 220-222
DTSTART;TZID=America/Los_Angeles:20250812T104500
DTEND;TZID=America/Los_Angeles:20250812T121500
UID:siggraph_SIGGRAPH 2025_sess150@linklings.com
SUMMARY:Motion From X
DESCRIPTION:Motion-example-controlled Co-speech Gesture Generation Leverag
 ing Large Language Models\n\nWe present a framework to utilize Large Langu
 age Models (LLMs) for co-speech gesture generation with motion examples as
  direct conditions. It enables multi-modal controls over co-speech gesture
  generation, such as motion clips, a single pose, human video, or even tex
 t prompts.\n\n\nBohong Chen (State Key Laboratory of CAD & CG, Zhejiang Un
 iversity) and Yumeng Li, Youyi Zheng, Yao-Xiang Ding, and Kun Zhou (State 
 Key Lab of CAD and CG, Zhejiang University)\n---------------------\nDuetGe
 n: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeli
 ng\n\nWe present a framework for generating music-driven synchronized two-
 person dance animations with close interactions. Our system represents the
  two-person motion sequence as a cohesive entity, performs hierarchical en
 coding of the motion sequence into discrete tokens, and utilizes dual gene
 rative mas...\n\n\nAnindita Ghosh (DFKI, Max Planck Institute for Informat
 ics); Bing Zhou (Snap Inc.); Rishabh Dabral (Max Planck Institute for Info
 rmatics); Jian Wang (Snap Inc.); Vladislav Golyanik and Christian Theobalt
  (Max Planck Institute for Informatics); Philipp Slusallek (DFKI, Saarland
  University); and Chuan Guo (Snap Inc.)\n---------------------\nxADA: Cont
 rollable and Expressive Audio-Driven Animation\n\nWe introduce xADA, a gen
 erative model for creating expressive and realistic animation of the face,
  tongue, and head directly from speech audio. \nThe animation maps directl
 y onto MetaHuman compatible rig controls enabling integration into industr
 y-standard content creation pipelines. \nxADA generalize...\n\n\nSarah Tay
 lor, Salvador Medina, Jonathan Windle, Erica Alcusa Sáez, and Iain Matthew
 s (Epic Games)\n---------------------\nSketch2Anim: Towards Transferring S
 ketch Storyboards into 3D Animation\n\nThis paper presents a novel and fir
 st approach - Sketch2Anim, to automatically translate 2D storyboard sketch
 es into high-quality 3D animations through multi-conditional motion genera
 tion.\n\n\nLei Zhong (University of Edinburgh), Chuan Guo (Snap Inc.), Yim
 ing Xie (Northeastern University), and Jiawei Wang and Changjian Li (Unive
 rsity of Edinburgh)\n---------------------\nSemantically Consistent Text-t
 o-Motion with Unsupervised Styles\n\nWe introduce a novel method that inte
 grates unsupervised style from arbitrary references into a text-driven dif
 fusion model to generate semantically consistent stylized human motion. We
  leverage text as a mediator to capture the temporal correspondences betwe
 en motion and style, enabling the seamles...\n\n\nLinjun Wu and Xiangjun T
 ang (Zhejiang University; State Key Laboratory of CAD&CG, Zhejiang Univers
 ity); Jingyuan Cong (University of California San Diego); He Wang (UCL Cen
 tre for Artificial Intelligence, Department of Computer Science, Universit
 y College London (UCL)); Bo Hu, Xu Gong, Songnan Li, and Yuchen Liao (Tenc
 ent Technology (Shenzhen) Co., Ltd.); Yiqian Wu (Zhejiang University); Che
 n Liu (State Key Lab of CAD and CG, Zhejiang University); and Xiaogang Jin
  (Zhejiang University; State Key Laboratory of CAD&CG, Zhejiang University
 )\n---------------------\nELGAR: Expressive Cello Performance Motion Gener
 ation for Audio Rendition\n\nGenerating string instrument performances wit
 h intricate movements and complex interactions poses significant challenge
 s. To address these, we present ELGAR—the first diffusion-based framework 
 for whole-body instrument performance motion generation solely from audio.
  We further contribute inno...\n\n\nZhiping Qiu and Yitong Jin (Central Co
 nservatory of Music, Tsinghua University); Yuan Wang (Central Conservatory
  of Music); Yi Shi (Central Conservatory of Music, Tsinghua University); C
 hao Tan (Weilan Tech); Chongwu Wang, Xiaobing Li, and Feng Yu (Central Con
 servatory of Music); and Tao Yu and Qionghai Dai (Tsinghua University)\n--
 -------------------\nMotion From X - Interactive Discussion\n\nAfter the s
 ummary presentations, attendees will participate in an interactive discuss
 ion. Outside the room will be a series of poster boards for authors to gat
 her around with the audience. Authors are invited to bring any material re
 lated to their paper that could instigate further conversation such...\n\n
 \nInterest Area: Research & Education\n\nRecording: Livestreamed, Not Live
 streamed, Recorded, Not Recorded\n\nRegistration Category: Full Conference
 , Virtual Access, Tuesday\n\nSession Chair: Sheldon Andrews (École de Tech
 nologie Supérieure (ÉTS), McGill University)
END:VEVENT
END:VCALENDAR