MambaCSP: Hybrid-Attention State Space Models for Hardware-Efficient Channel State Prediction

Computer Science > Information Theory [Submitted on 23 Apr 2026] MambaCSP: Hybrid-Attention State Space Models for Hardware-Efficient Channel State Prediction Aladin Djuhera, Haris Gacanin, Holger Boche Recent works have demonstrated that attention-based transformer and large language model (LLM) architectures can achieve strong channel state prediction (CSP) performance by capturing long-range temporal dependencies across channel state information (CSI) sequences. However, these models suffer from quadratic scaling in sequence length, leading to substantial computational cost, memory consumption, and inference latency, which limits their applicability in real-time and resource-constrained wireless deployments. In this paper, we investigate whether selective state space models (SSMs) can serve as a hardware-efficient alternative for CSI prediction. We propose MambaCSP, a hybrid-attention SSM architecture that replaces LLM-based prediction backbones with a linear-time Mamba model. To overcome the local-only dependencies of pure SSMs, we introduce lightweight patch-mixer attention layers that periodically inject cross-token attentions, helping with long-context CSI prediction. Extensive MISO-OFDM simulations show that MambaCSP improves prediction accuracy over LLM-based approaches by 9-12%, while delivering up to 3.0x higher throughput, 2.6x lower VRAM usage, and 2.9x faster inference. Our results demonstrate that hybrid state space architectures provide a promising direction for scalable and hardware-efficient AI-native CSI prediction in future wireless networks. Subjects: Information Theory (cs.IT); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Signal Processing (eess.SP) Cite as: arXiv:2604.21957 [cs.IT]   (or arXiv:2604.21957v1 [cs.IT] for this version)   https://doi.org/10.48550/arXiv.2604.21957 Focus to learn more Submission history From: Aladin Djuhera [view email] [v1] Thu, 23 Apr 2026 10:05:33 UTC (2,580 KB) Access Paper: HTML (experimental) view license Current browse context: cs.IT < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI cs.LG eess eess.SP math math.IT References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)