Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems
On the map: State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models
Abstract (arXiv)
Modeling interacting dynamical systems requires capturing spatial interactions alongside long-range temporal dependencies. Graph neural networks (GNNs) provide a natural representation but typically rely on autoregressive rollouts and treat spatial and temporal dynamics separately, leading to error accumulation over long horizons. Existing approaches also focus on local interactions and short temporal contexts, limiting their ability to capture multi-hop dependencies and global structure. We introduce the Graph Mamba Operator (GraMO), a latent-space simulator that integrates state-space models with graph-based interaction learning. In contrast to prior work that sequences nodes or applies spatial and temporal updates in separate stages, GraMO couples graph-based interactions and temporal state updates within a single recurrence. The update is linear in the latent state, with input-dependent coefficients that adapt across regimes. We evaluate GraMO on N-body systems, motion capture, and robotics datasets, achieving the lowest error across benchmarks and the largest gains in long-horizon prediction.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 42 of its 63 references that are in the map. First posted on arXiv 8 Jun 2026.
Builds on
42 of 63 references.
Closest ancestors · 2
Same direction, newest first
- 2024Graph Mamba: Towards Learning on Graphs with State Space Models13 Feb
- 2024Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces1 Feb
Other references · 40
- 2017Attention Is All You Needcited by 60,361
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
- 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
- 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
- 2021E(n) Equivariant Graph Neural Networkscited by 965
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
28 more
- 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
- 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
- 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
- 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 516
- 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
- 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 427
- 2018Neural Relational Inference for Interacting Systemscited by 339
- 2023Spherical Fourier Neural Operators: Learning Stable Dynamics on the Spherecited by 233
- 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 228
- 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 210
- 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 165
- 2021Learning Gradient Fields for Molecular Conformation Generationcited by 163
- 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
- 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
- 2018Flexible Neural Representation for Physics Predictioncited by 91
- 2022Equivariant Graph Mechanics Networks with Constraintscited by 68
- 2019Learning Compositional Koopman Operators for Model-Based Controlcited by 67
- 2022SocialVAE: Human Trajectory Prediction using Timewise Latentscited by 67
- 2019Equivariant Flows: sampling configurations for multi-body systems with symmetric energiescited by 57
- 2022Scalable Spatiotemporal Graph Neural Networkscited by 52
- 2024A Survey of Mambacited by 39
- 2024Equivariant Graph Neural Operator for Modeling 3D Dynamicscited by 38
- 2022Equivariant Graph Hierarchy-Based Neural Networkscited by 24
- 2023Spatio-Temporal Graph Neural Networks: A Surveycited by 23
- 2023EGraFFBench: Evaluation of Equivariant Graph Neural Network Force Fields for Atomistic Simulationscited by 15
- 2024Geometric Trajectory Diffusion Modelscited by 15
- 2025Latent Mamba Operator for Partial Differential Equationscited by 10
- 2024Graph Signal Adaptive Message Passingcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems
- 2024State-space models are accurate and efficient neural operators for dynamical systems
- 2024Topological Deep Learning with State-Space Models: A Mamba Approach for Simplicial Complexes
- 2024Enhanced Prediction of Multi-Agent Trajectories via Control Inference and State-Space Dynamics
- 2024STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model
- 2026Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies
- 2026Articulated-Body Dynamics Network: Dynamics-Grounded Prior for Robot Learning
- 2023Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems