Hybrid Neural World Models

• URL: http://arxiv.org/abs/2605.28317v1
• Date: Wed, 27 May 2026 11:17:08 GMT
• Title: Hybrid Neural World Models
• Abstract summary: Neural surrogates promise large speedups over classical solvers for physical dynamics but fail silently at sharp dynamical events such as shocks, fronts, and contact.<n>We present a recipe for training and deploying multi-horizon surrogates in physical state space.<n>The recipe applies without modification across reaction-diffusion, compressible Euler, and rigid-body collision dynamics.
• Score: 1.0742675209112622
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural surrogates promise large speedups over classical solvers for physical dynamics but fail silently at sharp dynamical events such as shocks, fronts, and contact. We present hybrid neural world models for physical dynamics: a recipe for training and deploying multi-horizon surrogates in physical state space, where a single network with continuous horizon conditioning is trained with direct supervision against textbook reference solvers to predict any future state at horizon T in one forward pass. Although no part of the training data, loss function, or architecture supervises discontinuity location, the trained surrogate encodes it implicitly, recoverable from its forward passes alone as a per-trajectory error map that concentrates on shocks, fronts, and contacts, and stays small elsewhere. The map is competitive with or better than standard label-free baselines including deep ensembles, learned error heads, gradient-magnitude indicators, and locally-adaptive conformal prediction, while using only a single trained network and requiring no calibration set or governing-equation knowledge. The recipe supports two operating points. Mode 1 runs the surrogate alone for maximum throughput, with same-hardware CPU speedups of 26x to 72x against textbook solvers on the PDE environments. Mode 2 uses the error map to gate a reference-solver fallback, deferring uncertain trajectories and roughly halving the surrogate's residual error at the default operating point. The recipe applies without modification across reaction-diffusion, compressible Euler, and rigid-body collision dynamics.

Related papers

• Rethinking Pre-Training and Augmentation for Zero-Shot Cross-City Object Detection [14.031215272664538]
  We propose a new training pipeline for object detection structured around two core pillars.<n>Our framework bridges cross-city distribution gaps while using limited GPU memory (16GB)<n>Our optimized variants, RF-DETR-HR and RF-DETR-Grayworld, deliver a substantial empirical gain of +24.29 over the baseline.
  arXiv  Detail & Related papers  (2026-08-25T07:16:42Z)
• FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows [18.746098727212544]
  FlowBender is a new diffusion and flow model for 3D reconstruction.<n>We show that FlowBender consistently outperforms standard supervised alignment training.<n>We propose several variants of FlowBender for differentiable operators.
  arXiv  Detail & Related papers  (2026-06-18T15:56:07Z)
• Physics from Video: Identifiability of Time-Invariant Second-Order ODEs under Minimal Trajectory Conditions [60.2784641643737]
  Bridging the gap between visual realism and physical understanding is a core challenge for video-based world models.<n>We study the structural identifiability of continuous-time physical laws from raw pixels.<n>We prove that a level-set slope-coverage condition ensures the learned latent space is locally affine to the true physical state.
  arXiv  Detail & Related papers  (2026-05-27T13:22:29Z)
• PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting [62.22445401483844]
  Existing methods are severely constrained by the bottleneck of compounding errors.<n>We propose a universal framework called -Cast-Corrector (Plug-and-Play Corrector)<n>Our method significantly enhances the long-term stability of coupled forecasting systems.
  arXiv  Detail & Related papers  (2026-05-09T13:12:33Z)
• SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere [90.85001795656633]
  Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos.<n>We propose SphereVAD, a fully training-free, zero-shot VAD framework that recasts anomaly discrimination as von Mises-Fisher (vMF) likelihood-ratio geodesic inference on the unit hypersphere.
  arXiv  Detail & Related papers  (2026-05-08T16:57:38Z)
• Zero-Shot Scalable Resilience in UAV Swarms: A Decentralized Imitation Learning Framework with Physics-Informed Graph Interactions [6.590573149504977]
  Large-scale Unmanned Aerial Vehicle (UAV) failures can split an unmanned aerial vehicle swarm network into disconnected sub-networks.<n>We present Physics-informed Adrial Graph Learning algorithm (PhyGAIL) that adopts centralized training with decentralized execution.
  arXiv  Detail & Related papers  (2026-04-17T07:06:42Z)
• DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks [54.32016216994156]
  We introduce the Causal Latent World Model (CLWM), which employs DINOv3 features as generative targets to disentangle interaction semantics from visual noise.<n>To overcome memory scaling, CLWM features a Dual-State Test-Time Training (TTT) Memory that guarantees a strict $mathcalO(1)$ footprint for long-horizon tasks.<n>We present EmbodiChain, an online framework that establishes the Efficiency Law by injecting an infinite flow of physics-grounded trajectories during training.
  arXiv  Detail & Related papers  (2026-04-13T03:19:36Z)
• Understanding Degradation with Vision Language Model [56.09241449206817]
  Understanding visual degradations is a critical yet challenging problem in computer vision.<n>We introduce DU-VLM, a multimodal chain-of-thought model trained with supervised fine-tuning and reinforcement learning.<n>We also introduce textbfDU-110k, a large-scale dataset comprising 110,000 clean-degraded pairs with grounded physical annotations.
  arXiv  Detail & Related papers  (2026-02-04T13:51:15Z)
• Unsupervised Physics-Informed Operator Learning through Multi-Stage Curriculum Training [1.5620806570871846]
  We introduce a physics-informed training strategy that achieves convergence by enforcing boundary conditions in the loss landscape.<n>At each stage the limitation is re-formed, acting as a continuation mechanism that restores stability and prevents stagnation.<n>Across canonical benchmarks, PhIS-FNO attains a level of accuracy comparable to that of supervised learning.
  arXiv  Detail & Related papers  (2026-02-02T16:06:57Z)
• Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation [8.973965016201822]
  Finding the right initialisation for neural networks is crucial to ensure smooth training and good performance.<n>In transformers, the wrong initialisation can lead to one of two failure modes of self-attention layers: rank collapse, where all tokens collapse into similar representations, and entropy collapse, where highly concentrated attention scores lead to instability.<n>Here, we provide an analytical theory of signal propagation through deep transformers with self-attention, layer normalisation, skip connections and gradients.
  arXiv  Detail & Related papers  (2025-05-30T08:18:23Z)
• HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters [53.97380482341493]
  "pre-train, prompt-tuning" has demonstrated impressive performance for tuning pre-trained heterogeneous graph neural networks (HGNNs) We propose a unified framework that combines two new adapters with potential labeled data extension to improve the generalization of pre-trained HGNN models.
  arXiv  Detail & Related papers  (2024-11-02T06:43:54Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)

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.