The paper introduces the Graph Dynamics Model (GDM), a world model that learns stochastic latent dynamics over evolving graph topologies. GDM employs a sparse recurrent adjacency matrix for topology updates and a recurrent state‑space architecture for stochastic transitions, enabling it to handle partially observable, stochastic environments. The authors also propose the Graph Distribution Distance (GDD) metric, using maximum mean discrepancy with a graph kernel, to compare predicted and true joint graph state distributions, and demonstrate GDM’s superior performance and zero‑shot generalisation on large graphs.
By Alex Schutz, Nick Hawes, Victor-Alexandru Darvariu
arXiv:2606. 04672v1 Announce Type: cross Abstract: Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data.
By Ayushman Raghuvanshi, Thummaluru Siddartha Readdy, Sundeep Prabhakar Chepuri, Mahesh Chandran
arXiv:2606. 14956v1 Announce Type: new Abstract: Autonomous driving systems rely on precise trajectory prediction to plan safe and efficient movement.
By George Daoud, Mohamed El-Darieby
arXiv:2608. 09031v1 Announce Type: new Abstract: Graph neural networks typically propagate information through repeated message-passing layers, coupling the distance over which information travels with the number of nonlinear transformations applied.
By Isuru Herath, Arin Gopakumar, Sharan Sahu
The paper introduces AdaptGNS, a particle simulation framework that dynamically adjusts the interaction graph based on per-particle uncertainty estimates. By training a variance head jointly with the acceleration head using a heteroscedastic Gaussian NLL loss, the model expands the neighborhood of high‑uncertainty particles, improving long‑horizon accuracy. Experiments show a strict Pareto improvement on the WaterDrop benchmark and a modest gain on Sand, suggesting adaptive graphs are especially beneficial in spatially complex regions.
By Aiden Zhou
arXiv:2609.38927v1 Announce Type: cross
Abstract: World models aim to learn representations of real-world environments and predict their future evolution. Recent object-centric world models have made...
By Yaqi Yang, Shuo Huang, Yujin Huang, Fucai Ke, Jiatong Han, Xin Zheng
arXiv:2606. 01283v1 Announce Type: new Abstract: Modeling spatial dependencies is central to spatiotemporal data analysis using Graph Neural Networks (GNNs).
By Zhongyue Zhang, Guangyin Jin, Yuxuan Liang, Suwan Yin, Yuankai Wu
arXiv:2509.12151v3 Announce Type: replace-cross
Abstract: We present a learnable physics-based model that predicts motion of the robot end effector and reaction force-torque in contact-rich manipulat...
By Zongyao Yi, Joachim Hertzberg, Martin Atzmueller
The paper introduces Newmark‑eta‑DGN, a graph neural network framework that learns coarse‑step dynamics and internal mechanical responses from discretely sampled trajectories. It combines a semi‑implicit update inspired by the Newmark‑eta method with an operator‑weighted virtual hub to capture system‑wide coupling. The model can predict long‑horizon motion and infer unobserved forces and stiffness operators across deformable beams, human gait, and protein dynamics without explicit supervision on mechanical quantities.
By Vinay Sharma, Olga Fink
The article surveys Dynamic Heterogeneous Graph Representation Learning (DHGRL), a field that tackles the challenges of modeling evolving, multi‑type networks. It introduces a unified definition covering both discrete‑time and continuous‑time DHGs, and proposes an algorithm‑centric taxonomy that groups methods into embedding‑based, GNN‑based, and Transformer‑based approaches, highlighting their biases toward temporal granularity. The survey also reviews key applications, datasets, benchmarks, and outlines future research directions.
By Huan Liu, Pengfei Jiao, Jie Yin, Hongjiang Chen, Zhidong Zhao
arXiv:2606. 09065v1 Announce Type: cross Abstract: In science and engineering, Lagrangian simulation methods such as Smooth Particle Hydrodynamics (SPH) or Material Point Method (MPM) are often employed to study the behavior of dynamic systems.
By Tu Do, Shannon Ryan, Santu Rana
arXiv:2606. 21295v2 Announce Type: replace-cross Abstract: Existing sequence models, including RNNs, LSTMs, continuous-time networks, and Transformers, share a common structural principle: layer-wise dynamics, where all neurons in the same layer co-evolve through a shared parameterized operator, leaving individual neurons no freedom to evolve independently.
By Borui Cai, Yao Zhao