Deep Wave Network for Modeling Multi-Scale Physical Dynamics

• URL: http://arxiv.org/abs/2605.04198v1
• Date: Tue, 05 May 2026 18:40:59 GMT
• Title: Deep Wave Network for Modeling Multi-Scale Physical Dynamics
• Abstract summary: Performance of deep learning models is strongly governed by capacity, with width and depth as primary controls.<n>In physical-science applications, models are often compared at a single fixed size or by separating accuracy and computational cost.<n>This issue is particularly relevant for U-Net-type encoder-decoder models, widely used for multi-scale gas, fluid, and plasma dynamics.
• Score: 39.146761527401424
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Performance of deep learning models is strongly governed by architectural capacity, with width and depth as primary controls. However, in physical-science applications, models are often compared at a single fixed size or by separating accuracy and computational cost, which can be misleading since architectures exhibit different accuracy-cost scaling as width and depth vary. This issue is particularly relevant for U-Net-type encoder-decoder models, widely used for multi-scale gas, fluid, and plasma dynamics due to their ability to represent features across spatial scales. A U-Net constructs a multi-resolution representation via an encoder that progressively reduces spatial resolution, followed by a decoder that restores it for prediction. Skip connections link corresponding encoder and decoder features, preserving fine-scale information and improving optimization. In practice, U-Net width is routinely tuned, while depth is typically kept fixed (a set number of down/up-sampling stages with few convolutions per stage), limiting systematic exploration of depth for improving the accuracy-cost trade-off. We address this limitation by increasing effective depth through stacking multiple encoder-decoder "waves" in series, with skip connections both within and across waves to enable progressive cross-scale refinement. We call this architecture a Deep Wave Network (DW-Net). Training data, optimization, and schedules are kept identical across models. Instead of evaluating single configurations, we train multiple width variants of each architecture and compare accuracy vs. GPU time Pareto fronts. Across several 2D and 3D flow benchmarks, DW-Net models consistently improve the Pareto frontier over single-wave U-Nets, achieving higher accuracy at matched cost or similar accuracy at reduced cost, and reaching low-error regimes with up to 3x less training time under identical training settings.

Related papers

• Variable-Width Transformers [57.07167443557886]
  We investigate nonuniform capacity allocation across network depth by proposing a $times$-shaped > former architecture.<n>Our design maintains wider early and late layers while narrowing the middle layers, utilizing a parameter-free residual resizing mechanism.<n>By reducing the average layer width, this architecture also requires fewer overall FLOPs and smaller KV cache memory and I/O cost.
  arXiv  Detail & Related papers  (2026-06-16T17:59:03Z)
• Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence [30.38509036690193]
  MOCHI is a multi-view 3D face prediction framework trained without requiring registered training data.<n>Standard point-to-surface distances induce training instabilities and visual artifacts in registration-free settings.<n>We propose pointmap- and normal-based losses instead, which provide smoother gradients and superior reconstruction fidelity.
  arXiv  Detail & Related papers  (2026-05-02T13:59:29Z)
• Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning [49.751529745537546]
  We propose DualOpt, a novel approach that decouples optimization techniques specifically tailored for training from scratch.<n>For training from scratch, we introduce real-time layer-wise weight decay, designed to enhance both convergence and generalization.<n>We extend the layer-wise weight decay to dynamically adjust the rollback levels across layers, adapting to the varying demands of different downstream tasks.
  arXiv  Detail & Related papers  (2026-04-21T06:27:18Z)
• Scale Propagation Network for Generalizable Depth Completion [16.733495588009184]
  We propose a novel scale propagation normalization (SP-Norm) method to propagate scales from input to output. We also develop a new network architecture based on SP-Norm and the ConvNeXt V2 backbone. Our model consistently achieves the best accuracy with faster speed and lower memory when compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-24T03:53:06Z)
• WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration [68.25711405944239]
  Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. We introduce a model-driven WiNet that incrementally estimates scale-wise wavelet coefficients for the displacement/velocity field across various scales.
  arXiv  Detail & Related papers  (2024-07-18T11:51:01Z)
• HYVE: Hybrid Vertex Encoder for Neural Distance Fields [9.40036617308303]
  We present a neural-network architecture suitable for accurate encoding of 3D shapes in a single forward pass. Our network is able to output valid signed distance fields without explicit prior knowledge of non-zero distance values or shape occupancy.
  arXiv  Detail & Related papers  (2023-10-10T14:07:37Z)
• Efficient Controllable Multi-Task Architectures [85.76598445904374]
  We propose a multi-task model consisting of a shared encoder and task-specific decoders where both encoder and decoder channel widths are slimmable. Our key idea is to control the task importance by varying the capacities of task-specific decoders, while controlling the total computational cost. This improves overall accuracy by allowing a stronger encoder for a given budget, increases control over computational cost, and delivers high-quality slimmed sub-architectures.
  arXiv  Detail & Related papers  (2023-08-22T19:09:56Z)
• Combined space-time reduced-order model with 3D deep convolution for extrapolating fluid dynamics [4.984601297028257]
  Deep learning-based reduced-order models have been recently shown to be effective in simulations. In this study, we aim to improve the extrapolation capability by modifying network architecture and integrating space-time physics as an implicit bias. To demonstrate the effectiveness of 3D convolution network, we consider a benchmark problem of the flow past a circular cylinder at laminar flow conditions.
  arXiv  Detail & Related papers  (2022-11-01T07:14:07Z)
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers [105.74546828182834]
  We show a hardware-efficient dynamic inference regime, named dynamic weight slicing, which adaptively slice a part of network parameters for inputs with diverse difficulty levels. We present dynamic slimmable network (DS-Net) and dynamic slice-able network (DS-Net++) by input-dependently adjusting filter numbers of CNNs and multiple dimensions in both CNNs and transformers.
  arXiv  Detail & Related papers  (2021-09-21T09:57:21Z)
• Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks [87.50632573601283]
  We present a novel method for multi-view depth estimation from a single video. Our method achieves temporally coherent depth estimation results by using a novel Epipolar Spatio-Temporal (EST) transformer. To reduce the computational cost, inspired by recent Mixture-of-Experts models, we design a compact hybrid network.
  arXiv  Detail & Related papers  (2020-11-26T04:04:21Z)
• ADCPNet: Adaptive Disparity Candidates Prediction Network for Efficient Real-Time Stereo Matching [8.046317778069325]
  coarse-to-fine method has largely relieved the memory constraints and speed limitations of large-scale network models. Previous coarse-to-fine designs employ constant offsets and three or more stages to progressively refine the coarse disparity map. This paper claims that the coarse matching errors can be corrected efficiently with fewer stages as long as more accurate disparity candidates can be provided.
  arXiv  Detail & Related papers  (2020-11-18T01:18:52Z)

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.