CSI-JEPA: Towards Foundation Representations for Ubiquitous Sensing with Minimal Supervision

• URL: http://arxiv.org/abs/2605.14171v1
• Date: Wed, 13 May 2026 22:50:31 GMT
• Title: CSI-JEPA: Towards Foundation Representations for Ubiquitous Sensing with Minimal Supervision
• Abstract summary: We present CSI-JEPA, a self-supervised predictive representation learning framework for label-efficient, multi-task Wi-Fi sensing.<n> CSI-JEPA learns reusable temporal-spectral representations from unlabeled CSI samples.<n>We evaluate CSI-JEPA on seven real-world Wi-Fi sensing tasks spanning diverse objectives and deployment settings.
• Score: 6.226207559281459
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Channel state information (CSI) provides a widely available sensing modality for human and environment perception, but existing CSI sensing models usually rely on task-specific supervised training and require substantial labeled data for each task, device, user, or environment. This limits their scalability in practical deployments where unlabeled CSI is abundant but labeled data is costly to collect. In this paper, we present CSI-JEPA, a self-supervised predictive representation learning framework for label-efficient, multi-task Wi-Fi sensing. CSI-JEPA learns reusable temporal-spectral representations from unlabeled CSI samples by predicting latent features of masked channel regions from visible context. To better match the physical structure of CSI, CSI-JEPA tokenizes channel-response amplitude windows along the time and subcarrier dimensions. It then introduces a channel variation-aware masking strategy that samples predictive targets from regions with stronger local temporal and subcarrier-domain variations. After pretraining, the encoder is frozen and used as a backbone, with lightweight task-specific adapters added for downstream sensing tasks. We evaluate CSI-JEPA on seven real-world Wi-Fi sensing tasks spanning diverse objectives and deployment settings. The results show that CSI-JEPA improves downstream sensing performance over competitive baselines, achieving up to 10.64 percentage points mean accuracy gain over state-of-the-art supervised Transformer and matched-budget label savings of up to 98.0%.

Related papers

• Learnware for CSI Feedback: Scene-specific Small Models Can Do Big [118.52196588174786]
  Intelligent channel state information (CSI) feedback is essential for realizing the high capacity and spectral efficiency goals of future 6G systems.<n>Existing deep learning solutions face a trade-off between model generalization and scenario-specific performance.<n>We introduce a model repository-based deployment framework in which a central AI data center maintains a catalog of scene-specific CSI models.
  arXiv  Detail & Related papers  (2026-08-18T13:26:34Z)
• WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation [0.6416429054645992]
  WiFi Channel State Information (CSI) enables privacy-preserving human pose sensing in camera-denied environments.<n>We propose WiFi-JEPA, a self-supervised framework that learns CSI-native representations by predicting masked latent embeddings.
  arXiv  Detail & Related papers  (2026-07-13T04:05:07Z)
• 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)
• 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)
• GNN-Enabled Robust Hybrid Beamforming with Score-Based CSI Generation and Denoising [105.08746566747324]
  We propose to utilize Graph Neural Networks (GNNs) and score-based generative models to enable robust Hybrid Beamforming (HBF) tasks.<n>We design a Bidirectional Representations from Transformers (BERT)-based Noise Conditional Score Network (NCSN) to learn the distribution of high-resolution CSI.<n>Finally, we present a Denoising Score Network (DSN) framework and its instantiation, termed DeBERT, which can denoise imperfect CSI under arbitrary channel error levels.
  arXiv  Detail & Related papers  (2025-11-10T03:18:34Z)
• Distributed Gossip-GAN for Low-overhead CSI Feedback Training in FDD mMIMO-OFDM Systems [65.23921727688749]
  We propose a novel gossiping generative adversarial network (Gossip-GAN)-aided CSI feedback training framework.<n>Gossip-GAN enables the CSI feedback training with low-overhead while preserving users' privacy.
  arXiv  Detail & Related papers  (2025-08-31T07:46:16Z)
• CSI-Bench: A Large-Scale In-the-Wild Dataset for Multi-task WiFi Sensing [13.709208651007167]
  WiFi sensing has emerged as a compelling contactless modality for human activity monitoring by capturing fine-grained variations in Channel State Information (CSI)<n>Existing WiFi sensing systems struggle to generalize in real-world settings due to datasets collected in controlled environments with homogeneous hardware and fragmented, session-based recordings that fail to reflect daily activity.<n>We present CSI-Bench, a large-scale, in-the-wild benchmark dataset collected using commercial WiFi edge devices across 26 diverse indoor environments with 35 real users.
  arXiv  Detail & Related papers  (2025-05-28T01:29:29Z)
• Lessons from Deploying Learning-based CSI Localization on a Large-Scale ISAC Platform [18.4186280784439]
  We explore the deployment of a large-scale CSI-based localization system involving over 400 Access Points (APs) in a real-world building under the Integrated Sensing and Communication (ISAC) paradigm.<n>We propose a novel CSI-based learning framework for WiFi localization, tailored for large-scale ISAC deployments on the server side.
  arXiv  Detail & Related papers  (2025-04-24T01:16:40Z)
• CSI-BERT2: A BERT-inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing [19.12026243010111]
  We propose a unified framework named CSI-BERT2 for CSI prediction and classification tasks.<n>The framework adapts BERT to capture the complex relationships among CSI sequences through a bidirectional self-attention mechanism.<n>Extensive experiments on both real-world collected and simulated datasets demonstrate that CSI-BERT2 achieves state-of-the-art performance across all tasks.
  arXiv  Detail & Related papers  (2024-12-09T06:44:04Z)
• Cross-domain Learning Framework for Tracking Users in RIS-aided Multi-band ISAC Systems with Sparse Labeled Data [55.70071704247794]
  Integrated sensing and communications (ISAC) is pivotal for 6G communications and is boosted by the rapid development of reconfigurable intelligent surfaces (RISs) This paper proposes the X2Track framework, where we model the tracking function by a hierarchical architecture, jointly utilizing multi-modal CSI indicators across multiple bands, and optimize it in a cross-domain manner. Under X2Track, we design an efficient deep learning algorithm to minimize tracking errors, based on transformer neural networks and adversarial learning techniques.
  arXiv  Detail & Related papers  (2024-05-10T08:04:27Z)
• ELGC-Net: Efficient Local-Global Context Aggregation for Remote Sensing Change Detection [65.59969454655996]
  We propose an efficient change detection framework, ELGC-Net, which leverages rich contextual information to precisely estimate change regions. Our proposed ELGC-Net sets a new state-of-the-art performance in remote sensing change detection benchmarks. We also introduce ELGC-Net-LW, a lighter variant with significantly reduced computational complexity, suitable for resource-constrained settings.
  arXiv  Detail & Related papers  (2024-03-26T17:46:25Z)
• RSCNet: Dynamic CSI Compression for Cloud-based WiFi Sensing [9.34104644481967]
  This paper develops a novel Real-time Sensing and Compression Network (RSCNet) which enables sensing with compressed CSI. RSCNet balances the trade-off between CSI compression and sensing precision, thus streamlining real-time cloud-based WiFi sensing with reduced communication costs. Numerical findings demonstrate the gains of RSCNet over the existing benchmarks like SenseFi, showcasing a sensing accuracy of 97.4% with minimal CSI reconstruction error.
  arXiv  Detail & Related papers  (2024-01-19T20:30:23Z)
• A Low-Overhead Incorporation-Extrapolation based Few-Shot CSI Feedback Framework for Massive MIMO Systems [45.22132581755417]
  Accurate channel state information (CSI) is essential for downlink precoding in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems. However, obtaining CSI through feedback from the user equipment (UE) becomes challenging with the increasing scale of antennas and subcarriers. Deep learning-based methods have emerged for compressing CSI but these methods require substantial collected samples. Existing deep learning methods also suffer from dramatically growing feedback overhead owing to their focus on full-dimensional CSI feedback. We propose a low-overhead-Extrapolation based Few-Shot CSI
  arXiv  Detail & Related papers  (2023-12-07T06:01:47Z)

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.