FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models

• URL: http://arxiv.org/abs/2603.21315v1
• Date: Sun, 22 Mar 2026 16:49:43 GMT
• Title: FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models
• Abstract summary: Current approaches default to Transformer-based predictors operating in learned latent spaces.<n>This paper asks a foundational question: is self-attention necessary for predictive world modeling, or can alternative computational substrates achieve comparable or superior results?<n>I introduce FluidWorld, a proof-of-concept world model whose predictive dynamics are governed by partial differential equations (PDEs) of reaction-diffusion type.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: World models learn to predict future states of an environment, enabling planning and mental simulation. Current approaches default to Transformer-based predictors operating in learned latent spaces. This comes at a cost: O(N^2) computation and no explicit spatial inductive bias. This paper asks a foundational question: is self-attention necessary for predictive world modeling, or can alternative computational substrates achieve comparable or superior results? I introduce FluidWorld, a proof-of-concept world model whose predictive dynamics are governed by partial differential equations (PDEs) of reaction-diffusion type. Instead of using a separate neural network predictor, the PDE integration itself produces the future state prediction. In a strictly parameter-matched three-way ablation on unconditional UCF-101 video prediction (64x64, ~800K parameters, identical encoder, decoder, losses, and data), FluidWorld is compared against both a Transformer baseline (self-attention) and a ConvLSTM baseline (convolutional recurrence). While all three models converge to comparable single-step prediction loss, FluidWorld achieves 2x lower reconstruction error, produces representations with 10-15% higher spatial structure preservation and 18-25% more effective dimensionality, and critically maintains coherent multi-step rollouts where both baselines degrade rapidly. All experiments were conducted on a single consumer-grade PC (Intel Core i5, NVIDIA RTX 4070 Ti), without any large-scale compute. These results establish that PDE-based dynamics, which natively provide O(N) spatial complexity, adaptive computation, and global spatial coherence through diffusion, are a viable and parameter-efficient alternative to both attention and convolutional recurrence for world modeling.

Related papers

• GPU-Accelerated Astrodynamics World Models for Spacecraft Rendezvous and Proximity Operations [21.666726162280696]
  This paper introduces a world model-based approach to cooperative and non-cooperative spacecraft rendezvous and proximity operations.<n>First, we introduce an open-source, JAX-based International Space Station (ISS) docking environment supporting parallel GPU simulation of spacecraft orbit and attitude dynamics.<n>Second, we introduce Out-of-this-World-Model, a transformer-based world model that encodes relative kinematic states and body-camera imagery into a latent state.<n>Third, we apply the approach to a capsule autonomously docking with the ISS under keep-out-zone constraints, demonstrating improved sample efficiency and task performance
  arXiv  Detail & Related papers  (2026-09-02T18:39:40Z)
• AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations Modeling [0.0]
  We propose a joint model consisting of a convolutional encoder, a transformer operating on latent representations, and a decoder for reconstruction.<n>Our approach combines the efficiency of latent evolution with the fidelity of full-field models, outperforming DL-ROMs, latent transformers, and plain ViTs in multi-field prediction.
  arXiv  Detail & Related papers  (2026-04-07T21:19:45Z)
• UniFluids: Unified Neural Operator Learning with Conditional Flow-matching [41.28751393724146]
  We present UniFluids, a conditional flow-matching framework to unify learning of solution operators across diverse PDEs.<n>UniFluids adopts flow-matching to achieve parallel sequence generation, making it the first such approach for unified operator learning.<n>We conduct a large-scale evaluation of UniFluids on several PDE datasets covering dimensions 1D, 2D and 3D.
  arXiv  Detail & Related papers  (2026-03-19T04:19:28Z)
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels [49.35636088613484]
  Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces.<n>We introduce LeModelWorld, the first JEPA that trains stably end-to-end from raw pixels using only two loss terms.<n>With 15M parameters trainable on a single GPU in a few hours, LeWM plans up to 48x faster than foundation-model-based world models.
  arXiv  Detail & Related papers  (2026-03-13T19:48:14Z)
• VFMF: World Modeling by Forecasting Vision Foundation Model Features [67.09340259579761]
  We introduce a generative forecaster that performs autoregressive flow matching in vision foundation models feature space.<n>We show that this latent information more effectively than previously used PCA-based alternatives, both for forecasting and other applications.<n>With matched architecture and compute, our method produces sharper and more accurate predictions than regression across all modalities.
  arXiv  Detail & Related papers  (2025-12-12T02:10:05Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• MORPH: Shape-agnostic PDE Foundation Models [37.26306668589026]
  MORPH is a shape-agnostic, autoregressive foundation model for partial differential equations (PDEs)<n>It is built on a convolutional vision backbone that seamlessly handles heterogeneous evaluations of varying data dimensionality (1D--3D)<n>Across extensive datasets, MORPH matches or surpasses strong baselines and recent state-of-the-art models.
  arXiv  Detail & Related papers  (2025-09-25T22:38:36Z)
• Scientific Machine Learning of Flow Resistance Using Universal Shallow Water Equations with Differentiable Programming [5.061700088495018]
  We developed a universal SWEs solver, Hydrograd, for hybrid hydrodynamics modeling.<n>It can do accurate forward simulations, support automatic differentiation, and perform scientific machine learning for physics discovery.
  arXiv  Detail & Related papers  (2025-02-18T00:07:14Z)
• Factorized Implicit Global Convolution for Automotive Computational Fluid Dynamics Prediction [52.32698071488864]
  We propose Factorized Implicit Global Convolution (FIGConv), a novel architecture that efficiently solves CFD problems for very large 3D meshes.<n>FIGConv achieves quadratic complexity $O(N2)$, a significant improvement over existing 3D neural CFD models.<n>We validate our approach on the industry-standard Ahmed body dataset and the large-scale DrivAerNet dataset.
  arXiv  Detail & Related papers  (2025-02-06T18:57:57Z)
• BCAT: A Block Causal Transformer for PDE Foundation Models for Fluid Dynamics [4.027470328330335]
  We introduce BCAT, a PDE foundation model designed for autoregressive prediction of solutions to two dimensional fluid dynamics problems.<n>Our approach uses a block causal architecture to model next frame predictions, leveraging previous frames as contextual priors rather than relying solely on sub-frames or pixel-based inputs commonly used in image generation methods.
  arXiv  Detail & Related papers  (2025-01-31T09:07:56Z)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models [49.81937966106691]
  We develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models. In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach.
  arXiv  Detail & Related papers  (2023-06-15T16:30:08Z)
• MAgNet: Mesh Agnostic Neural PDE Solver [68.8204255655161]
  Climate predictions require fine-temporal resolutions to resolve all turbulent scales in the fluid simulations. Current numerical model solveers PDEs on grids that are too coarse (3km to 200km on each side) We design a novel architecture that predicts the spatially continuous solution of a PDE given a spatial position query.
  arXiv  Detail & Related papers  (2022-10-11T14:52:20Z)
• Emulating Spatio-Temporal Realizations of Three-Dimensional Isotropic Turbulence via Deep Sequence Learning Models [24.025975236316842]
  We use a data-driven approach to model a three-dimensional turbulent flow using cutting-edge Deep Learning techniques. The accuracy of the model is assessed using statistical and physics-based metrics.
  arXiv  Detail & Related papers  (2021-12-07T03:33:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.