Structured Latent Dynamics in Wireless CSI via Homomorphic World Models

• URL: http://arxiv.org/abs/2603.20048v1
• Date: Fri, 20 Mar 2026 15:32:47 GMT
• Title: Structured Latent Dynamics in Wireless CSI via Homomorphic World Models
• Abstract summary: We introduce a self-supervised framework for learning predictive and structured representations of wireless channels by modeling the temporal evolution of state information (CSI) in a compact latent space.<n>Our method casts the problem as a world modeling task and leverages the Joint Embedding Predictive Architecture (JEPA) to learn action-conditioned latent dynamics from CSI trajectories.
• Score: 39.38895182380197
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce a self-supervised framework for learning predictive and structured representations of wireless channels by modeling the temporal evolution of channel state information (CSI) in a compact latent space. Our method casts the problem as a world modeling task and leverages the Joint Embedding Predictive Architecture (JEPA) to learn action-conditioned latent dynamics from CSI trajectories. To promote geometric consistency and compositionality, we parameterize transitions using homomorphic updates derived from Lie algebra, yielding a structured latent space that reflects spatial layout and user motion. Evaluations on the DICHASUS dataset show that our approach outperforms strong baselines in preserving topology and forecasting future embeddings across unseen environments. The resulting latent space enables metrically faithful channel charts, offering a scalable foundation for downstream applications such as mobility-aware scheduling, localization, and wireless scene understanding.

Related papers

• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• The Global Neural World Model: Spatially Grounded Discrete Topologies for Action-Conditioned Planning [0.9137554315375919]
  We present the Global Neural World Model (GNWM), a self-stabilizing framework that achieves topological quantization.<n> operating as a continuous, action-conditioned Joint-Embedding Predictive Architecture (JEPA)<n>Our results show this architecture prevents manifold drift during autoregressive rollouts by using grid snapping'' as a native error-correction mechanism.
  arXiv  Detail & Related papers  (2026-04-17T15:12:15Z)
• Wireless Traffic Prediction with Large Language Model [54.07581399989292]
  TIDES is a novel framework that captures spatial-temporal correlations for wireless traffic prediction.<n> TIDES achieves efficient adaptation to domain-specific patterns without incurring excessive training overhead.<n>Our results indicate that integrating spatial awareness into LLM-based predictors is the key to unlocking scalable and intelligent network management in future 6G systems.
  arXiv  Detail & Related papers  (2025-12-19T04:47:40Z)
• STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization [29.10084723132903]
  We propose an innovative Spatio-Temporal Retrieval-Augmented Pattern Learning framework, STRAP.<n>During inference, STRAP retrieves relevant patterns from this library based on similarity to the current input and injects them into the model via a plug-and-play prompting mechanism.<n>Experiments across multiple real-world streaming graph datasets show that STRAP consistently outperforms state-of-the-art STGNN baselines on STOOD tasks.
  arXiv  Detail & Related papers  (2025-05-26T06:11:05Z)
• Geometry-aware Active Learning of Spatiotemporal Dynamic Systems [4.251030047034566]
  This paper proposes a geometry-aware active learning framework for modeling dynamic systems.<n>We develop an adaptive active learning strategy to strategically identify spatial locations for data collection and further maximize the prediction accuracy.
  arXiv  Detail & Related papers  (2025-04-26T19:56:38Z)
• Towards Scalable Foundation Model for Multi-modal and Hyperspectral Geospatial Data [14.104497777255137]
  We introduce Low-rank Efficient Spatial-Spectral Vision Transformer with three key innovations.<n>We pretrain LESS ViT using a Hyperspectral Masked Autoencoder framework with integrated positional and channel masking strategies.<n> Experimental results demonstrate that our proposed method achieves competitive performance against state-of-the-art multi-modal geospatial foundation models.
  arXiv  Detail & Related papers  (2025-03-17T05:42:19Z)
• Learning Latent Wireless Dynamics from Channel State Information [31.080933663717257]
  We propose a novel data-driven machine learning (ML) technique to model and predict the dynamics of the wireless propagation environment in latent space. We present numerical evaluations on measured data and show that the proposed JEPA displays a two-fold increase in accuracy over benchmarks.
  arXiv  Detail & Related papers  (2024-09-16T07:15:46Z)
• Context-Conditioned Spatio-Temporal Predictive Learning for Reliable V2V Channel Prediction [25.688521281119037]
  Vehicle-to-Vehicle (V2V) channel state information (CSI) prediction is challenging and crucial for optimizing downstream tasks. Traditional prediction approaches focus on four-dimensional (4D) CSI, which includes predictions over time, bandwidth, and antenna (TX and RX) space. We propose a novel context-conditionedtemporal predictive learning method to capture dependencies within 4D CSI data.
  arXiv  Detail & Related papers  (2024-09-16T04:15:36Z)
• Temporal Predictive Coding For Model-Based Planning In Latent Space [80.99554006174093]
  We present an information-theoretic approach that employs temporal predictive coding to encode elements in the environment that can be predicted across time. We evaluate our model on a challenging modification of standard DMControl tasks where the background is replaced with natural videos that contain complex but irrelevant information to the planning task.
  arXiv  Detail & Related papers  (2021-06-14T04:31:15Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• On the spatial attention in Spatio-Temporal Graph Convolutional Networks for skeleton-based human action recognition [97.14064057840089]
  Graphal networks (GCNs) promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a graph. Most of the recently proposed G-temporal-based methods improve the performance by learning the graph structure at each layer of the network.
  arXiv  Detail & Related papers  (2020-11-07T19:03:04Z)

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.