Latent Generative Solvers for Generalizable Long-Term Physics Simulation
Reliable physics simulation demands two capabilities that today's neural PDE solvers do not deliver together: generalization across heterogeneous PDE families, and stability under long autoregressive rollouts. Deterministic operators accumulate error geometrically, while existing probabilistic solvers are confined to a single PDE family or short horizons. We close this gap with the \textbf{Latent Generative Solver} (LGS), three coupled components: (i) a Physics VAE (PhyVAE) compressing twelve PDE families into a shared latent manifold; (ii) a Pyramidal Flow-Forcing Transformer (PFlowFT) that generates the next latent by flow matching, conditioned on a per-trajectory context updated on the model's own predictions; and (iii) input noising during training, for which we derive a sufficient-condition contraction bound explaining the observed long-horizon stability. Pretrained on a 2.5\,M-trajectory, 16-system corpus at $128^2$, LGS matches the strongest deterministic baseline at one step, wins on 15/16 systems at both 5- and 10-step rollout, cuts 20-step L2RE from $56.1\%$ to $\mathbf{30.2\%}$, and uses $\mathbf{13}$--$\mathbf{77\times}$ less recurrent dynamics-step compute. It also adapts efficiently to a $256^2$ Kolmogorov flow held out from the pretraining corpus, dropping 1-step L2RE from $0.398$ to $0.129$ in five finetune epochs against U-AFNO's $0.653{\to}0.343$.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics
Deep learning has emerged as a promising paradigm for spatio-temporal modeling of fluid dynamics. However, existing approaches often suffer from limited generalization to unseen flow conditions and typically require retr…
Out-of-Distribution Generalization for Neural Physics Solvers
Neural physics solvers are increasingly used in scientific discovery, given their potential for rapid in silico insights into physical, materials, or biological systems and their long-time evolution. However, poor genera…
Generative Latent Neural PDE Solver using Flow Matching
Autoregressive next-step prediction models have become the de-facto standard for building data-driven neural solvers to forecast time-dependent partial differential equations (PDEs). Denoise training that is closely rela…
Uncertainty QuantificationTowards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection
Endowing machines with abstract reasoning ability has been a long-term research topic in artificial intelligence. Raven's Progressive Matrix (RPM) is widely used to probe abstract visual reasoning in machine intelligence…
Answer GenerationAttributeOdd One OutVisual ReasoningTowards Scalable One-Step Generative Modeling for Autoregressive Dynamical System Forecasting
Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently while preserving the statistical structure of long trajectories. Neural oper…