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:20260417T190111Z
LOCATION:West Building\, Rooms 118-120
DTSTART;TZID=America/Los_Angeles:20250813T090000
DTEND;TZID=America/Los_Angeles:20250813T103000
UID:siggraph_SIGGRAPH 2025_sess137@linklings.com
SUMMARY:Robots in the World
DESCRIPTION:Designing Pin-pression Gripper and Learning its Dexterous Gras
 ping with Online In-hand Adjustment\n\nWe introduce a pin-pression gripper
  featuring parallel-jaw fingers with 2D arrays of independently extendable
  pins, allowing instant shape adaptation to target object geometry and dyn
 amic in-hand re-orientation for enhanced grasp stability. Reinforcement le
 arning with curriculum-based training enabl...\n\n\nHewen Xiao and Xiuping
  Liu (Dalian University of Technology), Hang Zhao (Wuhan University), Jian
  Liu (Shenyang University of Technology), and Kai Xu (National University 
 of Defense Technology (NUDT))\n---------------------\nCueTip: An Interacti
 ve and Explainable Physics-aware Pool Assistant\n\nCueTip is an interactiv
 e and explainable automated coaching assistant for a variant of pool/billi
 ards. CueTip has a natural-language interface, the ability to perform cont
 extual, physics-aware reasoning, and its explanations are rooted in a set 
 of predetermined guidelines developed by domain experts...\n\n\nSean Memer
 y and Kevin Denamganaï (University of Edinburgh), Jiaxin Zhang and Zehai T
 u (Lightspeed Studios), Yiwen Guo (Independent), and Kartic Subr (Universi
 ty of Edinburgh)\n---------------------\nAerial Path Online Planning for U
 rban Scene Updation\n\nWe present the first scene-update aerial path plann
 ing algorithm specifically designed for detecting and updating change area
 s in urban environments, which paves the way for efficient, scalable, and 
 adaptive UAV-based scene updates in complex urban environments.\n\n\nMingf
 eng Tang (Shenzhen University), Ningna Wang (University of Texas at Dallas
 ), Ziyuan Xie (Shenzhen University), Jianwei Hu (QiYuan Lab), Ke Xie (Shen
 zhen University), Xiaohu Guo (University of Texas at Dallas), and Hui Huan
 g (Shenzhen University)\n---------------------\nAMOR: Adaptive Character C
 ontrol through Multi-Objective Reinforcement Learning\n\nPresenting AMOR, 
 a policy conditioned on context and a linear combination of reward weights
 , trained using multi-objective reinforcement learning. Once trained, AMOR
  allows for on-the-fly adjustments of reward weights, unlocking new possib
 ilities in physics-based and robotic character control.\n\n\nLucas N. Aleg
 re (Instituto de Informática - Universidade Federal do Rio Grande do Sul, 
 Disney Research) and Agon Serifi, Ruben Grandia, David Müller, Espen Knoop
 , and Moritz Bächer (Disney Research)\n---------------------\nRobots in th
 e World - Interactive Discussion\n\nAfter the summary presentations, atten
 dees will participate in an interactive discussion. Outside the room will 
 be a series of poster boards for authors to gather around with the audienc
 e. Authors are invited to bring any material related to their paper that c
 ould instigate further conversation such...\n\n---------------------\nLear
 ning to Assemble with Alternative Plans\n\nWe introduce a reinforcement le
 arning framework for assembling structures composed of rigid parts. A pre-
 trained policy generates alternative assembly plans, enabling rapid adapta
 tion to unexpected disruptions. Our approach supports efficient and robust
  planning for multi-robot assembly tasks.\n\n\nZiqi Wang (HKUST, EPFL); We
 njun Liu (HKUST); Jingwen Wang and Gabriel Vallat (EPFL); Fan Shi (Nationa
 l University of Singapore); and Stefana Parascho and Maryam Kamgarpour (EP
 FL)\n---------------------\nCreating Fluid-Interactive Virtual Agents by a
 n Efficient Simulator with Local-domain Control\n\nWe introduce a novel lo
 cal-domain fluid-solid interaction simulator grounded in a lattice Boltzma
 nn solver. By leveraging an MPC-based domain-tracking approach and an impr
 oved convective boundary condition, it offers enhanced stability and effic
 iency for deriving control policies of virtual agents, ...\n\n\nWenbin Son
 g, Heng Zhang, Yang Wang, and Xiaopei Liu (ShanghaiTech University)\n\nInt
 erest Area: Research & Education\n\nRecording: Livestreamed, Not Livestrea
 med, Recorded, Not Recorded\n\nRegistration Category: Full Conference, Vir
 tual Access, Wednesday\n\nSession Chair: Paul Kry (McGill University)
END:VEVENT
END:VCALENDAR