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:20260805T205457Z
LOCATION:Room 403 A
DTSTART;TZID=America/Los_Angeles:20260723T140000
DTEND;TZID=America/Los_Angeles:20260723T153000
UID:siggraph_SIGGRAPH 2026_sess105@linklings.com
SUMMARY:Learning in Motion
DESCRIPTION:R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh 
 Flow\n\nWe present R-DMesh, a novel feed-forward video-guided mesh animati
 on framework that solves the pose misalignment dilemma between an initial 
 mesh and a condition video through jump offset modeling. It generates high
 -fidelity, motion aligned 4D animations and enables downstream application
 s like pose ...\n\n\nZijie Wu (Huazhong University of Science and Technolo
 gy, Tencent Hunyuan); Lixin Xu, Puhua Jiang, Sicong Liu, and Chunchao Guo 
 (Tencent Hunyuan); and Xiang Bai (Huazhong University of Science and Techn
 ology)\n---------------------\nTopoCap: Learning Topology-Agnostic Motion 
 Priors for Monocular Video-to-Animation\n\nTopoCap is a unified framework 
 for motion capture and retargeting from monocular video, supporting arbitr
 ary skeletal topologies without test-time optimization. Leveraging a two-s
 tage generative pipeline, TopoCap achieves motion transfer across diverse 
 creatures, backed by Mobjaverse—a dataset...\n\n\nChengfeng Pu, Jia-Peng Z
 hang, and Meng-Hao Guo (CS Dept, Tsinghua University); Yan-Pei Cao (VAST);
  and Shi-Min Hu (CS Dept, Tsinghua University)\n---------------------\nSty
 lized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptatio
 n\n\nWe propose a hypernetwork-driven LoRA framework for stylized text-to-
 motion generation that dynamically modulates a pretrained diffusion model 
 using style embeddings extracted from reference motions. By structuring th
 e style latent space with supervised contrastive learning and incorporatin
 g style-g...\n\n\nJunhyuk Jeon, Seokhyeon Hong, and Junyong Noh (Korea Adv
 anced Institute of Science and Technology (KAIST))\n---------------------\
 nMUSIC: Learning Muscle-Driven Dexterous Hand Control\n\nWe present a data
 -driven framework for physics-based, muscle-driven dexterous control that 
 enables musculoskeletal hands to perform piano playing for novel musical s
 cores. Our framework adopts a hierarchical architecture, combining high-fr
 equency muscle control with low-frequency coordination. The m...\n\n\nPei 
 Xu and Yufei Ye (Stanford University); Shuchu Sun (Clemson University); an
 d Yu Ding, Elizabeth Schumann, and C. Karen Liu (Stanford University)\n---
 ------------------\nMOCHI: Motion Enhancement of Collaborative Human-objec
 t Interactions\n\nOur method enhances noisy multi-human object interaction
  (MHOI) data by automatically generating plausible hand and finger motions
  and refining noisy body movements, all while preserving the original inte
 raction semantics.\n\n\nJiye Lee, Yonghun Choi, and Jungdam Won (Seoul Nat
 ional University)\n---------------------\nACT: A Unified Framework for Rig
 ging and Animating Characters with Arbitrary Topologies\n\nACT is a unifie
 d AI framework that effortlessly brings static 3D characters to life. By i
 ntegrating rigging, skinning, and motion generation into a single diffusio
 n-based pipeline, ACT automatically animates characters of any shape, deli
 vering high-quality, physically plausible motions that overcome...\n\n\nPe
 ngyu Long (ShanghaiTech University, ByteDance Games); Weirui Wang (Shangha
 iTech University, Deemos Technology); Qingcheng Zhao (University of Toront
 o, Deemos Technology); Xiaoyang Guo and Xiaoyu Pan (ByteDance Games); Qixu
 an Zhang (ShanghaiTech University, Deemos Technology); Jiaqing Zhou and Ti
 anlei Hu (ByteDance Games); Wei Yang (Huazhong University of Science and T
 echnology); and Lan Xu and Jingyi Yu (ShanghaiTech University)\n----------
 -----------\nLearning in Motion - Interactive Discussion\n\nAfter the summ
 ary presentations, attendees will participate in an interactive discussion
 . Outside the room will be a series of poster boards for authors to gather
  around with the audience. Authors are invited to bring any material relat
 ed to their paper that could instigate further conversation such...\n\n\nI
 nterest Area: Research & Education\n\nKeyword: Animation, Artificial Intel
 ligence/Machine Learning, Modeling, Simulation\n\nRegistration Category: F
 ull Conference Supporter, Full Conference\n\nSession Chair: Min Lu (Shenzh
 en University (SZU))
END:VEVENT
END:VCALENDAR