BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
X-LIC-LOCATION:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:19911015T033000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251218T030656Z
LOCATION:Meeting Room S221\, Level 2
DTSTART;TZID=Asia/Hong_Kong:20251218T111200
DTEND;TZID=Asia/Hong_Kong:20251218T112300
UID:siggraphasia_SIGGRAPH Asia 2025_sess153_papers_1970@linklings.com
SUMMARY:Uni-Inter Unifying 3D Human Motion Synthesis Across Diverse Intera
 ction Contexts
DESCRIPTION:Sheng Liu (Nanjing University); Yuanzhi Liang and Jiepeng Wang
  (Institute of Artificial Intelligence, China Telecom (TeleAI)); Sidan Du 
 (Nanjing University); and Chi Zhang and Xuelong Li (Institute of Artificia
 l Intelligence, China Telecom (TeleAI))\n\nWe present Uni-Inter, a unified
  framework for human motion generation that supports a wide range of inter
 action scenarios—including human-human, human-object, and human-scene—with
 in a single, task-agnostic architecture. In contrast to existing methods t
 hat rely on task-specific designs and exhibit limited generalization, Uni-
 Inter introduces the Unified Interactive Volume (UIV), a volumetric repres
 entation that encodes heterogeneous interactive entities into a shared spa
 tial field. This enables consistent relational reasoning and compound inte
 raction modeling. Motion generation is formulated as joint-wise probabilis
 tic prediction over the UIV, allowing the model to capture fine-grained sp
 atial dependencies and produce coherent, context-aware behaviors. Experime
 nts across three representative interaction tasks demonstrate that Uni-Int
 er achieves competitive performance and generalizes well to novel combinat
 ions of entities. These results suggest that unified modeling of compound 
 interactions offers a promising direction for scalable motion synthesis in
  complex environments. Additionally, our code will be open-sourced in the 
 future to support further research and development in this area.\n\nRegist
 ration Category: Full Access, Full Access Supporter\n\nSession Chair: Kai 
 Wang (Simon Fraser University)\n\n
END:VEVENT
END:VCALENDAR