Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models

• URL: http://arxiv.org/abs/2605.00968v1
• Date: Fri, 01 May 2026 15:51:10 GMT
• Title: Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models
• Abstract summary: Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization of performance wireless foundation models.<n>This paper proposes Adaptive 3D-RoPE, a physics-aligned rotary positional encoding that establishes the structural corner?stone for wireless foundation models.
• Score: 14.956130211673894
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization performance of wireless foundation models for channel state information (CSI) modeling, latent characterization, and task-specific prediction. However, existing CSI models inherit static or one-dimensional positional priors from natural language and vision architectures, which fundamentally misalign with the intrinsic physics of wireless channels by lacking explicit relative decay, collapsing the 3D spatio-temporal-frequency structure, and remaining scenario?rigid. This paper proposes Adaptive 3D-RoPE, a physics-aligned rotary positional encoding that establishes the structural corner?stone for wireless foundation models. The framework integrates a learnable, axis-decoupled 3D frequency bank to explicitly disentangle multi-dimensional phase dependencies, coupled with a lightweight channel-conditioned controller that dynamically modulates the prior via compact global CSI descriptors. This sample-adaptive mechanism transforms positional encoding from a static transformer component into a dynamic, coherence-aware inductive bias to resolve heterogeneous channel physics. Extensive experiments across 100 datasets demonstrate the superiority of the proposed scheme in both scale extrapolation and zero-shot generalization. Compared to the state-of-the-art, our method achieves up to a 10.7 dB reduction in normalized mean square error (NMSE) under 8 times antenna scale extrapolation. Given the same CSI input scales, our method can also improve zero-shot NMSE by 1.07 dB across unseen mobility scenarios and 0.90 dB in low-frequency-to-millimeter-wave tasks.

Related papers

• GSBF: Gaussian Splatting for Environment-Aware Beamforming [38.39752476018955]
  We develop a 3D Gaussian splatting for environment-aware beamforming (GSBF) pipeline based on multi-fold data.<n>GSBF consistently outperforms baselines such as exhaustive beam alignment (EBA) with lower latency.
  arXiv  Detail & Related papers  (2026-08-06T11:22:34Z)
• Fast Cross-Scenario Adaptation of CSI Models via Channel Conditional Parameter Generation [71.49439535846827]
  Conditional Channel Generation (CCPG) is an end-to-end pipeline for rapid deployment of CSI models in dynamic wireless environments.<n> CCPG identifies scene-sensitive adaptation bottlenecks through component-freezing experiments and generates only lightweight LoRA weights.<n>Experiments on DeepMIMO and WAIR-D for CSI feedback and channel estimation show that CCPG adapts to new scenarios in about 3 seconds with a single forward pass.
  arXiv  Detail & Related papers  (2026-06-22T13:20:01Z)
• Mesh Based Simulations with Spatial and Temporal awareness [2.867517731896504]
  We propose a unified framework to bridge the gap between geometric deep learning and rigorous numerical analysis.<n>We introduce three key innovations: (1) Multi Node Prediction, a stencil-level objective that predicts field values for a node's full local topology, enforcing spatial derivative consistency; (2) Temporal Correction, replacing unstable explicit schemes with a predictor-corrector via temporal Cross-Attention; and (3) Geometric Inductive Biases, leveraging 3D Rotary Positional Embeddings (RoPE) to robustly capture rotational symmetries in unstructured meshes.
  arXiv  Detail & Related papers  (2026-05-02T17:09:31Z)
• Implicit Neural Representations: A Signal Processing Perspective [54.57279006229212]
  Implicit neural representations (INRs) mark a fundamental shift in signal modeling, moving from discrete sampled data to continuous functional representations.<n>This article examines the evolution of INRs from a signal processing perspective, emphasizing spectral behavior, sampling theory, and multiscale representation.<n>We highlight the utility of INRs across a broad range of applications, including inverse problems in medical and radar imaging, compression, and 3D scene representation.
  arXiv  Detail & Related papers  (2026-04-16T14:12:06Z)
• Learning high-dimensional quantum entanglement through physics-guided neural networks [9.690823115015908]
  We propose a physics-guided deep neural network that reconstructs the source's modal fingerprint.<n>Across gain regimes, our method achieves high-fidelity reconstruction with average JSD of 1.96e-3, WEMD of 1.54e-3, and KL divergence of 7.85e-3.<n>These results demonstrate that physics-guided learning, via a soft OAM-conservation regularizer and physically generated training targets, enables rapid and data-efficient modal characterization.
  arXiv  Detail & Related papers  (2026-04-03T22:09:21Z)
• Generative MIMO Beam Map Construction for Location Recovery and Beam Tracking [67.65578956523403]
  This paper proposes a generative framework to recover location labels directly from sparse channel state information (CSI) measurements.<n>Instead of directly storing raw CSI, we learn a compact low-dimensional radio map embedding and leverage a generative model to reconstruct the high-dimensional CSI.<n> Numerical experiments demonstrate that the proposed model can improve localization accuracy by over 30% and achieve a 20% capacity gain in non-line-of-sight (NLOS) scenarios.
  arXiv  Detail & Related papers  (2025-11-21T07:25:49Z)
• SenseRay-3D: Generalizable and Physics-Informed Framework for End-to-End Indoor Propagation Modeling [35.27031919957894]
  SenseRay-3D is an end-to-end framework that predicts 3D path-loss heatmaps directly from RGB-D scans.<n>A synthetic indoor propagation dataset is developed to serve as a standardized benchmark for future research.<n> SenseRay-3D achieves a mean absolute error of 4.27 dB on unseen environments and supports real-time inference at 217 ms per sample.
  arXiv  Detail & Related papers  (2025-11-15T08:17:49Z)
• Multi-View Wireless Sensing via Conditional Generative Learning: Framework and Model Design [16.839582722091635]
  We incorporate physical knowledge into learning-based high-precision target sensing using the multi-view channel state information (CSI) between multiple base stations (BSs) and user equipment (UEs)<n>We design a bipartite neural network architecture, the first part of which uses an elaborately designed encoder to fuse the latent target features embedded in the multi-view CSI.<n>The second part uses them as conditioning inputs of a powerful generative model to guide the target's reconstruction.
  arXiv  Detail & Related papers  (2025-05-19T03:27:24Z)
• Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image Classification [12.168520751389622]
  KANet is an improved 3D-DenseNet model, consisting of 3D KAN Conv and an adaptive grid update mechanism.<n> KANet enhances model representation capability through a 3D dynamic expert convolution system without increasing network depth or width.<n>The proposed method demonstrates superior performance on IN, UP, and KSC datasets, outperforming mainstream hyperspectral image classification approaches.
  arXiv  Detail & Related papers  (2025-04-21T14:57:48Z)
• 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction [50.07071392673984]
  Existing methods learn 3D rotations parametrized in the spatial domain using angles or quaternions. We propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression. Our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+.
  arXiv  Detail & Related papers  (2024-11-01T12:50:38Z)
• NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions [93.02515761070201]
  We present a novel type of neural fields that uses general radial bases for signal representation. Our method builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals. When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed.
  arXiv  Detail & Related papers  (2023-09-27T06:32:05Z)
• PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation [54.734201944510026]
  We propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix.<n>In a nutshell, our auxiliary network learns to fix local variants intensively by effectively back-propagating local information through the meta-gradient.<n>This network is model-agnostic, so can be used in any kind of architectures in a plug-and-play manner.
  arXiv  Detail & Related papers  (2022-07-27T07:48:29Z)

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.