Physics-Based Simulation

Follow this topic Ask about this topic

Momentum

19 papers in the last four weeks, up 217% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 152

All topics

A Neural Hierarchical-Matrix Preconditioner for Real-Time GPU Solves
May 13, 2026Carl Osborne, Minghao Guo, Crystal Owens +1Graph Neural Networks High-Performance Computing
MIT CSAIL, Cambridge, USA
Crash Assessment via Mesh-Based Graph Neural Networks and Physics-Aware Attention
May 12, 2026Gabriel Curtosi, Carlos Manuel Ruiz Ruiz, Fabiola Cavaliere +1Neural Surrogate Modeling Graph Neural Networks
SEAT S.A., Barcelona, Spain · IDIADA Automotive Technology S.A., Santa Oliva, Spain
UAV-Assisted Scan-to-Simulation for Landslides Using Physics-Informed Gaussian Splatting
May 11, 2026Zhenyu Liang, Jack C. P. Cheng3D Gaussian Splatting Physics-Based Simulation
HKUST
PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions
May 10, 2026Jihyun Lee, Changmin Lee, Donghwan Kim +13D Reconstruction Deformable Shape Reconstruction
School of Computing, KAIST, Daejeon, South Korea.
Enabling Structure-Only Initialization and Out-of-Distribution Generalization in GNN-based Molecular Dynamics Simulators
May 10, 2026S. A. Shteingolts, Salman N. Salman, Dan MendelsGraph Neural Networks OOD Generalization
The Wolfson Department of Chemical Engineering, Technion - Israel Institute of Technology, Haifa, 32000, Israel
Your Simulation Runs but Solves the Wrong Physics: PDE-Grounded Intent Verification for LLM-Generated Multiphysics Simulation Code
May 10, 2026Zhenghan Song, Yulong Liu, Cheng Wan +4LLM Self-Correction Scientific Code Generation
Cornell University · Columbia University · Harvard University & Nanyang Technological University
M $^3$ : Reframing Training Measures for Discretized Physical Simulations
May 9, 2026Yuan Mei, Xingyu Song, Xiaowen Song +1Neural Surrogate Modeling Adaptive Sampling
1Zhejiang University · *Visiting student at The University of Tokyo from Zhejiang University. · 2The University of Tokyo
SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics
May 8, 2026Yicheng Zhu, Yang Chen, Tao Li +1GPU Acceleration Vehicle Dynamics
Rochester Institute of Technology · City University of Hong Kong
CarCrashNet: A Large-Scale Dataset and Hierarchical Neural Solver for Data-Driven Structural Crash Simulation
May 8, 2026Mohamed Elrefaie, Dule Shu, Matthew Klenk +1Neural Surrogate Modeling Structural Mechanics
Department of Mechanical Engineering MIT Cambridge, MA, USA · Future Product Innovation Toyota Research Institute Los Altos, CA, USA
BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation
May 7, 2026Richard Hildebrandt, Evangelos Kourlitis, Baran Hashemi +7Neural Surrogate Modeling Riemannian Flow Matching
Technical University of Munich · Max-Planck Institute for Mathematics in the Sciences, Leipzig, Germany · SLAC National Accelerator Laboratory +3
Variational Matrix-Learning Fourier Networks for Parametric Multiphysics Surrogates
May 4, 2026Xinyu Li, Jianhua Zhang, Liang ChenPDE Surrogate Modeling Physics-Informed ML
School of Microelectronics, Shanghai University, Shanghai 201800, China
Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics
May 1, 2026Satoshi Noguchi, Yoshinobu KawaharaDynamical Systems Scientific ML
Center for Mathematical Science and Advanced Technology, JAMSTEC · Center for Advanced Intelligence Project, RIKEN · Graduate School of Information Science and Technology, The University of Osaka.
An ALE-Consistent Graph Neural Operator-Transformer Framework for Fluid-Structure Interaction
May 1, 2026Shihang Zhao, Martín Saravia, Haokui Jiang +2PDE Surrogate Modeling Physics-Based Simulation
Institute for Ocean Engineering, Shenzhen International Graduate School, Tsinghua University, Shenzhen, Guangdong, 518055, China · Centro de Investigación en Mecánica Teórica y Aplicada, Universidad Tecnológica Nacional - CONICET, 11 de Abril 461, Bahía Blanca, Argentina
FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
Apr 30, 2026Qianfan Shen, Ningxiao Tao, Qiyu Dai +63D Gaussian Splatting Physics-Based Simulation
School of EECS, Peking University · School of Intelligence Science and Technology, Peking University · 3Yuanpei College, Peking University +3
CRADIPOR: Crash Dispersion Predictor
Apr 30, 2026Edgar Chaillou, Sebastian Rodriguez, Yves Tourbier +1Physics-Based Simulation
PIMM, Arts et Métiers Institute of Technology, Paris, France · Renault Group, Guyancourt, France
Momentum-Conserving Graph Neural Networks for Deformable Objects
Apr 28, 2026Jiahong Wang, Logan Numerow, Stelian Coros +3Graph Neural Networks Physics-Informed ML
Max Planck Institute for Informatics · ETH Zurich · University of Bonn +1
Avionic Main Fuel Pump Simulation and Fault-Diagnosis Benchmark
Apr 23, 2026Felix Leonhard Janzen, Lukas Moddemann, Alexander Diedrich +1Fault Detection Unsupervised Anomaly Detection
Institute of Artificial Intelligence
Agentic AI-Enabled Framework for Thermal Comfort and Building Energy Assessment in Tropical Urban Neighborhoods
Apr 23, 2026Po-Yen Lai, Xinyu Yang, Derrick Low +2LLM Agents Physics-Based Simulation
Institute of High Performance Computing (IHPC), Agency for Science Technology and Research (A*STAR), 1 Fusionopolis Way, #16-16 Connexis, Singapore 138632, Republic of Singapore.
The High Explosives and Affected Targets (HEAT) Dataset
Apr 20, 2026Bryan Kaiser, Kyle Hickmann, Sharmistha Chakrabarti +6Surrogate Modeling Synthetic Benchmark Generation
Los Alamos National Laboratory
FLASH: Fast Learning via GPU-Accelerated Simulation for High-Fidelity Deformable Manipulation in Minutes
Apr 19, 2026Siyuan Luo, Bingyang Zhou, Chong Zhang +9Contact-Rich Robotic Manipulation Robotics Simulation
NUS Human-Centered Robotic Lab · ETH · ShanghaiTech University +2
DataCenterGym: A Physics-Grounded Simulator for Multi-Objective Data Center Scheduling
Apr 17, 2026Nilavra Pathak, Samadrita Biswas, Nirmalya RoyModel Predictive Control Physics-Based Simulation
Marketing Data Science, Expedia Group · Analytical Development, Curia Global · Department of Information Systems, University of Maryland, Baltimore County
PolyJarvis: An LLM-Orchestrated Agent for Automated All-Atom Molecular Dynamics of Amorphous Homopolymers
Apr 2, 2026Alexander Zhao, Achuth Chandrasekhar, Amir Barati FarimaniMaterials Property Prediction Materials Science
Department of Materials Science and Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA · Department of Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA
Fire as a Service: Augmenting Robot Simulators with Thermally and Visually Accurate Fire Dynamics
Mar 19, 2026Anton R. Wagner, Madhan Balaji Rao, Helge Wrede +2Robotics Simulation Synthetic Data Generation for Robotics
Department of Computer Science, Kiel University, Germany · Department of Computer Science, George Mason University, USA
Early-Terminable Energy-Safe Iterative Coupling for Parallel Simulation of Partitioned Port-Hamiltonian Systems
Mar 17, 2026Qi Wei, Jianfeng Tao, Hongyu Nie +1Dynamical Systems Port-Hamiltonian Systems
School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Discovering High Level Patterns from Simulation Traces
Feb 10, 2026Sean Memery, Kartic SubrLLM Grounding Program Synthesis
University of Edinburgh, United Kingdom
Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics
Jan 29, 2026Winfried Ripken, Michael Plainer, Gregor Lied +5Dynamical Systems Flow Map Learning
Technical University Berlin · BIFOLD · Free University of Berlin +6
AllShowers: One model for all calorimeter showers
Jan 16, 2026Thorsten Buss, Henry Day-Hall, Frank Gaede +2Neural Surrogate Modeling Generative Modeling
Institut für Experimentalphysik, Universität Hamburg, Hamburg, Germany · Deutsches Elektronen-Synchrotron DESY, Hamburg, Germany
Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
Nov 19, 2025Michael McCabe, Payel Mukhopadhyay, Tanya Marwah +22Physics-Based Simulation Computational Fluid Dynamics
Polymathic AI · Flatiron Institute · New York University +9
Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy
Oct 2, 2025Meir H. Shachar, Dane M. Sterbentz, Harshitha Menon +10Multi-Agent LLM Systems AI Agents for Scientific Discovery
Lawrence Livermore National Laboratory Livermore, CA, USA · Lawrence Livermore National Laboratory Livermore, CA 94550, USA · Sandia National Laboratories Albuquerque, NM, USA +3
Learning 3D-Gaussian Simulators from RGB Videos
Mar 31, 2025Mikel Zhobro, Andreas René Geist, Georg MartiusPhysical Consistency in Video Generation Physics-Based Simulation
University of Tübingen, Germany

May 13, 2026, cs.GRJ/K move · Enter open · S save

A Neural Hierarchical-Matrix Preconditioner for Real-Time GPU Solves

Carl Osborne, Minghao Guo, Crystal Owens, Wojciech Matusik

MIT CSAIL, Cambridge, USA

Graph Neural Networks High-Performance Computing Physics-Based Simulation

Open paper AskPDF arXiv

Interactive simulation solves Ax=b for a sparse SPD A that changes every frame, inside an 8-16 ms budget. At a few thousand unknowns, the setup of algebraic multigrid alone exceeds that budget, while Jacobi and other local preconditioners have no setup but cannot move error across the domain. We learn a preconditioner for this gap: a graph-and-attention network predicts an SPD approximate inverse in H^2-matrix format. On a spatially ordered 3D mesh, blocks of the true inverse lose rank as the clusters they couple move apart; the nested bases of the format follow that decay, so inference and apply are dominated by leaf-block work linear in N, where a dense inverse costs N^2. Our main finding concerns training. Probe losses reach M only through a product with A, so their gradient vanishes on the near-null modes that set the conjugate-gradient iteration count. A truncated Kaporin condition number has no such factor; changing only the objective cuts iterations on a held-out frame from 116 to 33. On a ladder of stiff tetrahedral diffusion problems ours alone fits an 8.3 ms (120 fps) frame from N=572 to 3,647.

Momentum

Related topics

Latest papers 152