Towards CSI-Native Foundation Models: A Channel-Adaptive Roadmap for 6G

• URL: http://arxiv.org/abs/2606.20670v1
• Date: Fri, 12 Jun 2026 11:01:12 GMT
• Title: Towards CSI-Native Foundation Models: A Channel-Adaptive Roadmap for 6G
• Abstract summary: Wireless foundation models offer a path toward reusable channel state information (CSI) intelligence for sixth-generation (6G) systems.<n>Existing generic-backbone adaptation and CSI pretraining methods often treat CSI as task tensors rather than propagation-conditioned channel responses.<n>This paper proposes a unified framework that aligns pretraining, positional modeling, and attention control with three channel requirements.
• Score: 14.956130211673894
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Wireless foundation models offer a path toward reusable channel state information (CSI) intelligence for sixth-generation (6G) systems. However, existing generic-backbone adaptation and CSI pretraining methods often treat CSI as task tensors rather than propagation-conditioned channel responses, thereby failing to capture the intrinsic time-frequency-spatial geometry of wireless environments. This paper presents a channel-adaptive roadmap toward CSI-native foundation models, proposing a unified framework that aligns pretraining, positional modeling, and attention control with three channel requirements: scale-aware heterogeneous exposure, physical time-frequency-antenna coordinates, and correlation-bounded token interaction. Extensive experiments demonstrate the superiority of the proposed framework across three dimensions: zero-shot generalization, reducing NMSE by more than 4 dB across spatial-temporal-frequency tasks; scale extrapolation, yielding up to a 5.4 dB gain under 8 times unseen antenna scaling; and inference efficiency, accelerating mobility-aware processing by up to 18.8%. A system-level evaluation with Sionna SYS further shows that the proposed framework uses only 7.01% of dense-pilot overhead, reaches -18.64 dB average NMSE, and improves average net spectral efficiency by 36.6% over dense LMMSE and 15.5% over WiFo, indicating that CSI-native representation learning can support pilot-efficient radio access.

Related papers

• WALoMA: A Multitask Wireless Foundation Model via Adaptive Low-Rank Masked Autoencoders [23.225139930889526]
  This paper proposes a multitask wireless foundation model via adaptive low-rank masked autoencoders (WALoMA)<n>It addresses the limitations of specialized, task-specific deep learning models and the practical challenge of scarce labeled wireless datasets.
  arXiv  Detail & Related papers  (2026-07-28T14:18:22Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• ArcGate: Adaptive Arctangent Gated Activation [62.5098969984518]
  This paper proposes the Adaptive Arctangent Gated Activation function, a flexible formulation that generates a broad spectrum of activation shapes.<n>We evaluate ArcGate on three widely used remote sensing benchmarks: PatternNet, UC Merced Land Use, and the 13-band EuroSAT MSI multispectral dataset.
  arXiv  Detail & Related papers  (2026-05-14T08:00:46Z)
• HeterCSI: Channel-Adaptive Heterogeneous CSI Pretraining Framework for Generalized Wireless Foundation Models [24.285127409979342]
  HeterCSI is a channel-adaptive pretraining framework that reconciles training efficiency with robust cross-scenario generalization.<n>HeterCSI achieves superior average performance over full-shot baselines.<n>Compared to the state-of-the-art benchmark WiFo, it reduces NMSE by 7.19 dB, 4.08 dB, and 5.27 dB for CSI reconstruction, time-domain, and frequency-domain prediction, respectively.
  arXiv  Detail & Related papers  (2026-01-26T06:35:48Z)
• LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G [85.58816960936069]
  Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Time (Near-RT) latency and computational constraints.<n>This paper investigates a post-Transformer paradigm for efficient radio telemetry forecasting.<n>We propose a quantum-inspired state-space tensor network that replaces self-attention with stable structured state-space dynamics kernels.
  arXiv  Detail & Related papers  (2026-01-18T12:08:38Z)
• GSpaRC: Gaussian Splatting for Real-time Reconstruction of RF Channels [18.70495617397063]
  Channel state information (CSI) is essential for adaptive beamforming and robust links in wireless communication systems.<n>We present GSpaRC: Gaussian Splatting for Real-time Reconstruction of RF Channels, the first computation to break the 1 ms latency barrier.
  arXiv  Detail & Related papers  (2025-11-27T22:42:23Z)
• 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)
• Green Learning for STAR-RIS mmWave Systems with Implicit CSI [53.03358325565645]
  Green learning (GL)-based precoding framework is proposed for simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided millimeter-wave (mmWave) broadcasting systems.<n>Motivated by the emphasis on environmental sustainability in future 6G networks, this work adopts a transmission framework for scenarios where multiple users share identical information, improving spectral efficiency and reducing redundant transmissions and power consumption.
  arXiv  Detail & Related papers  (2025-09-08T15:56:06Z)
• RF-PGS: Fully-structured Spatial Wireless Channel Representation with Planar Gaussian Splatting [3.3008315224941973]
  This paper proposes RF-PGS, a novel framework that reconstructs high-fidelity radio propagation paths from only sparse path loss spectra.<n>Compared to prior radiance field methods, RF-PGS significantly improves reconstruction accuracy, reduces training costs, and enables efficient representation of wireless channels.
  arXiv  Detail & Related papers  (2025-08-23T00:33:21Z)
• Standards-Compliant DM-RS Allocation via Temporal Channel Prediction for Massive MIMO Systems [4.251030047034567]
  We introduce the concept of channel prediction-based reference signal allocation (CPRS)<n>CPRS jointly optimize channel prediction and DM-RS allocation to improve data throughput without requiring CSI feedback.<n>We show up to 36.60% throughput improvement over benchmark strategies.
  arXiv  Detail & Related papers  (2025-07-15T07:56:37Z)
• Deep Learning-Based Synchronization for Uplink NB-IoT [72.86843435313048]
  We propose a neural network (NN)-based algorithm for device detection and time of arrival (ToA) estimation for the narrowband physical random-access channel (NPRACH) of narrowband internet of things (NB-IoT) The introduced NN architecture leverages residual convolutional networks as well as knowledge of the preamble structure of the 5G New Radio (5G NR) specifications.
  arXiv  Detail & Related papers  (2022-05-22T12:16:43Z)
• Three-Way Deep Neural Network for Radio Frequency Map Generation and Source Localization [67.93423427193055]
  Monitoring wireless spectrum over spatial, temporal, and frequency domains will become a critical feature in beyond-5G and 6G communication technologies. In this paper, we present a Generative Adversarial Network (GAN) machine learning model to interpolate irregularly distributed measurements across the spatial domain.
  arXiv  Detail & Related papers  (2021-11-23T22:25:10Z)

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.