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:20260805T205458Z
LOCATION:Room 403  B
DTSTART;TZID=America/Los_Angeles:20260722T140000
DTEND;TZID=America/Los_Angeles:20260722T153000
UID:siggraph_SIGGRAPH 2026_sess184@linklings.com
SUMMARY:Differentiable Geometry Processing & Flow Maps
DESCRIPTION:Iskra: A System for Inverse Geometry Processing\n\nIskra is a 
 system for differentiating through solutions to geometry processing proble
 ms.\nIt differentiates a broad class of algorithms, exploiting existing fa
 st problem-specific schemes common to geometry processing, including local
 -global and ADMM solvers. It is compatible with machine learning fra...\n\
 n\nAna Dodik, Ahmed Mahmoud, and Justin Solomon (Massachusetts Institute o
 f Technology (MIT))\n---------------------\nSharpNet: Enhancing MLPs to Re
 present Functions with Controlled Non-differentiability\n\nWe propose Shar
 pNet, an enhanced MLP architecture that augments the input with a feature 
 function to produce controllable derivative jumps. We show that SharpNet c
 an preserve the sharpness in the intended regions while maintaining smooth
 ness elsewhere, and that it outperforms baseline methods in sha...\n\n\nHa
 nting Niu (Institute of Software, Chinese Academy of Sciences; University 
 of Chinese Academy of Sciences); Junkai Deng (Nanyang Technological Univer
 sity); Fei Hou and Wencheng Wang (Institute of Software, Chinese Academy o
 f Sciences; University of Chinese Academy of Sciences); and Ying He (Nanya
 ng Technological University)\n---------------------\nSchrödinger Bridges o
 n Discretized Geometric Domains\n\nWe introduce a spatially discrete formu
 lation of the Schrödinger bridge problem on meshes and grids that enables 
 structure-preserving interpolation between probability distributions. We d
 emonstrate our approach across mesh- and grid-based applications, includin
 g displacement interpolation, shape int...\n\n\nLeticia Mattos Da Silva, M
 ohammad Sina Nabizadeh, and Justin Solomon (Massachusetts Institute of Tec
 hnology (MIT))\n---------------------\nExplicit flows for implicit surface
 s\n\nOur paper presents a method for shape-morphing and deformation using 
 an exact mathematical flow. We introduce a neural architecture guaranteed 
 to encode a flow, leveraging implicit supervision of explicit flows, ensur
 ing topological consistency and efficient forward/inverse computation with
 out ODE s...\n\n\nCamille Buonomo (CNRS - LIRIS); Julie Digne (CNRS, LIRIS
 ); and Raphaëlle Chaine (CNRS - LIRIS)\n---------------------\nA Few-Step 
 Generative Model on Cumulative Flow Maps\n\nWe propose a unified few-step 
 generative framework based on cumulative flow maps for long-range transpor
 t in probability space. By connecting instantaneous updates with finite-ti
 me transport, it applies broadly to diffusion and flow models, supports fe
 w-step and one-step generation, requires minimal...\n\n\nZhiqi Li, Duowen 
 Chen, Yuchen Sun, and Bo Zhu (Georgia Institute of Technology)\n----------
 -----------\nGenerative Modeling with Orbit-Space Particle Flow Matching\n
 \nOrbit-Space Geometric Probability Paths (OGPP) is a flow-matching framew
 ork for generative modeling of particle systems that exploits shared geome
 tric structure and uses probability path geometry to encode geometric info
 rmation. It enables high-quality, efficient generation of particle configu
 ration...\n\n\nSinan Wang, Jinjin He, Shenyifan Lu, Ruicheng Wang, Greg Tu
 rk, and Bo Zhu (Georgia Institute of Technology)\n---------------------\nD
 ifferentiable Geometry Processing & Flow Maps - Interactive Discussion\n\n
 After the summary presentations, attendees will participate in an interact
 ive discussion. Outside the room will be a series of poster boards for aut
 hors to gather around with the audience. Authors are invited to bring any 
 material related to their paper that could instigate further conversation 
 such...\n\n\nInterest Area: Research & Education\n\nKeyword: Artificial In
 telligence/Machine Learning, Geometry, Modeling\n\nRegistration Category: 
 Full Conference Supporter, Full Conference\n\nSession Chair: Nicholas Shar
 p (NVIDIA)
END:VEVENT
END:VCALENDAR