DRIFT-Net: A Spectral--Coupled Neural Operator for PDEs Learning

• URL: http://arxiv.org/abs/2509.24868v1
• Date: Mon, 29 Sep 2025 14:52:31 GMT
• Title: DRIFT-Net: A Spectral--Coupled Neural Operator for PDEs Learning
• Abstract summary: We propose textbfDRIFT-Net for learning PDE dynamics with neural solvers.<n>It employs a dual-branch design comprising a spectral branch and an image branch.<n>It achieves lower error and higher throughput with fewer parameters under identical training settings and budget.
• Score: 16.6687431452785
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning PDE dynamics with neural solvers can significantly improve wall-clock efficiency and accuracy compared with classical numerical solvers. In recent years, foundation models for PDEs have largely adopted multi-scale windowed self-attention, with the scOT backbone in \textsc{Poseidon} serving as a representative example. However, because of their locality, truly globally consistent spectral coupling can only be propagated gradually through deep stacking and window shifting. This weakens global coupling and leads to error accumulation and drift during closed-loop rollouts. To address this, we propose \textbf{DRIFT-Net}. It employs a dual-branch design comprising a spectral branch and an image branch. The spectral branch is responsible for capturing global, large-scale low-frequency information, whereas the image branch focuses on local details and nonstationary structures. Specifically, we first perform controlled, lightweight mixing within the low-frequency range. Then we fuse the spectral and image paths at each layer via bandwise weighting, which avoids the width inflation and training instability caused by naive concatenation. The fused result is transformed back into the spatial domain and added to the image branch, thereby preserving both global structure and high-frequency details across scales. Compared with strong attention-based baselines, DRIFT-Net achieves lower error and higher throughput with fewer parameters under identical training settings and budget. On Navier--Stokes benchmarks, the relative $L_{1}$ error is reduced by 7\%--54\%, the parameter count decreases by about 15\%, and the throughput remains higher than scOT. Ablation studies and theoretical analyses further demonstrate the stability and effectiveness of this design. The code is available at https://github.com/cruiseresearchgroup/DRIFT-Net.

Related papers

• ScaLe-INR: Scale and Learn Implicit Neural Representations [0.0]
  Implicit Neural Representations (INRs) parameterized by multilayer perceptrons excel at modeling continuous signals.<n>High-frequency weight updates destructively interfere with the underlying low-frequency structural approximation.<n>ScaLe-INR explicitly matches the signal's frequency spectrum with the optimal operating region of the INR.
  arXiv  Detail & Related papers  (2026-06-26T09:02:48Z)
• Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion [46.51681899437508]
  We introduce Spectral Forcing, a parameter-free, time-conditional 2D-DCT low-pass operator applied to the noisy input before the patch embedder.<n>Its cutoff expands monotonically with the diffusion time and becomes the identity at the data endpoint.<n>On ImageNet-256 with JiT-700M/32, Spectral Forcing consistently improves both FID and Inception Score across different training epochs.
  arXiv  Detail & Related papers  (2026-06-13T10:29:11Z)
• Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation [50.139984798361375]
  We propose a training-free framework that removes redundancy via latent discrepancy.<n> LD-Pruning substantially reduces inference while maintaining high generation quality, achieving up to 2.35x speedup on Infinity-8B.
  arXiv  Detail & Related papers  (2026-05-29T19:34:39Z)
• Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment [27.352639822596146]
  Cross-worker divergence in losses and gradients can remain invisible under conventional monitoring signals.<n>We propose a model-agnostic diagnostic framework that quantifies worker-level consistency using training signals readily available in standard pipelines.
  arXiv  Detail & Related papers  (2026-02-16T04:42:30Z)
• Unbiased Gradient Estimation for Event Binning via Functional Backpropagation [64.88399635309918]
  We propose a novel framework for unbiased gradient estimation of arbitrary binning functions by synthesizing weak derivatives during backpropagation.<n>We achieve 9.4% lower EPE in self-supervised optical flow, and 5.1% lower RMS error in SLAM, demonstrating broad benefits for event-based visual perception.
  arXiv  Detail & Related papers  (2026-02-13T04:05:03Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning [85.20505958752928]
  Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment.<n>RFT often introduce visual hallucinations like over-optimized details and semantic misalignment.<n>This work preliminarily explores why visual hallucinations arise and how to reduce them.
  arXiv  Detail & Related papers  (2026-02-03T11:49:46Z)
• Task-Driven Prompt Learning: A Joint Framework for Multi-modal Cloud Removal and Segmentation [11.468907022707013]
  TDP-CR is a task-driven framework that jointly performs cloud removal and land-cover segmentation.<n>Central to our approach is a Prompt-Guided Fusion mechanism, which utilizes a learnable degradation prompt to encode cloud thickness and spatial uncertainty.<n>Experiments on the LuojiaSET-OSFCR dataset demonstrate the superiority of our framework.
  arXiv  Detail & Related papers  (2026-01-17T13:32:38Z)
• Harnessing Optimization Dynamics for Curvature-Informed Model Merging [17.42364575754576]
  In supervised fine-tuning, multiple capability-based SFT checkpoints must be consolidated into a single model.<n>We introduce Optimization Trajectory Aware (OTA) Merging and Fast Fisher Grafting (FFG)<n>OTA+FFG improves merged-model quality over strong weight-space baselines, reduces negative transfer, and remains robust across sparsity levels.
  arXiv  Detail & Related papers  (2025-09-14T08:59:53Z)
• Gaussian Primitive Optimized Deformable Retinal Image Registration [19.882820812725523]
  Deformable retinal image registration is notoriously difficult due to large homogeneous regions and sparse but critical vascular features.<n>We introduce a novel iterative framework that performs structured message passing to overcome these challenges.<n>Experiments on the FIRE dataset show that GPO reduces the target registration error from 6.2,px to 2.4,px and increases the AUC at 25,px from 0.770 to 0.938.
  arXiv  Detail & Related papers  (2025-08-23T00:44:50Z)
• PiT: Progressive Diffusion Transformer [50.46345527963736]
  Diffusion Transformers (DiTs) achieve remarkable performance within image generation via the transformer architecture.<n>We find that DiTs do not rely as heavily on global information as previously believed.<n>We propose a series of Pseudo Progressive Diffusion Transformer (PiT)
  arXiv  Detail & Related papers  (2025-05-19T15:02:33Z)
• How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings [106.3726679697804]
  We compare the two most common techniques for mitigating this spectral bias: Fourier feature encodings (FFE) and multigrid parametric encodings (MPE)<n>MPEs are seen as the standard for low dimensional mappings, but MPEs often outperform them and learn representations with higher resolution and finer detail.<n>We prove that MPEs improve a network's performance through the structure of their grid and not their learnable embedding.
  arXiv  Detail & Related papers  (2025-04-18T02:18:08Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Degradation-Noise-Aware Deep Unfolding Transformer for Hyperspectral Image Denoising [9.119226249676501]
  Hyperspectral images (HSIs) are often quite noisy because of narrow band spectral filtering. To reduce the noise in HSI data cubes, both model-driven and learning-based denoising algorithms have been proposed. This paper proposes a Degradation-Noise-Aware Unfolding Network (DNA-Net) that addresses these issues.
  arXiv  Detail & Related papers  (2023-05-06T13:28:20Z)
• A differentiable short-time Fourier transform with respect to the window length [4.0527583944137255]
  We revisit the use of spectrograms in neural networks, by making the window length a continuous parameter optimizable by descent gradient. The contribution is mostly theoretical at this point, but plugging the modified STFT into any existing neural network is straightforward.
  arXiv  Detail & Related papers  (2022-08-23T11:38:33Z)
• Magic ELF: Image Deraining Meets Association Learning and Transformer [63.761812092934576]
  This paper aims to unify CNN and Transformer to take advantage of their learning merits for image deraining. A novel multi-input attention module (MAM) is proposed to associate rain removal and background recovery. Our proposed method (dubbed as ELF) outperforms the state-of-the-art approach (MPRNet) by 0.25 dB on average.
  arXiv  Detail & Related papers  (2022-07-21T12:50:54Z)
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning [62.52242684874278]
  Cross-modality distribution of spatial and spectral information makes the problem challenging. We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net. Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
  arXiv  Detail & Related papers  (2020-06-18T06:32:11Z)

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.