Turbo-ICL: In-Context Learning-Based Turbo Equalization
This addresses signal processing challenges in wireless communications, offering a novel approach for improving equalization in non-linear conditions, though it is incremental as it adapts existing ICL methods to a specific domain.
The paper tackled channel equalization in coded MIMO systems by introducing an in-context learning framework that infers symbol distributions from pilot signals and decoder feedback, achieving performance gains over conventional baselines even with perfect channel state information, particularly in scenarios like low-resolution quantization.
This paper introduces a novel in-context learning (ICL) framework, inspired by large language models (LLMs), for soft-input soft-output channel equalization in coded multiple-input multiple-output (MIMO) systems. The proposed approach learns to infer posterior symbol distributions directly from a prompt of pilot signals and decoder feedback. A key innovation is the use of prompt augmentation to incorporate extrinsic information from the decoder output as additional context, enabling the ICL model to refine its symbol estimates iteratively across turbo decoding iterations. Two model variants, based on Transformer and state-space architectures, are developed and evaluated. Extensive simulations demonstrate that, when traditional linear assumptions break down, e.g., in the presence of low-resolution quantization, ICL equalizers consistently outperform conventional model-based baselines, even when the latter are provided with perfect channel state information. Results also highlight the advantage of Transformer-based models under limited training diversity, as well as the efficiency of state-space models in resource-constrained scenarios.