Deep polar codes are a class of pre-transformed polar codes that employ a multi-layered polar kernel transformation strategy to enhance code performance in short blocklength regimes. However, like conventional polar codes, their block length is constrained to powers of two, as the final transformation layer uses a conventional polar kernel matrix. In this paper, we propose a novel rate-matching technique for deep polar codes using a code extension methodology, particularly effective when the desired code length slightly exceeds a power of two. The key idea is to exploit the layered structure of deep polar codes by concatenating polar codewords generated at each layer. Based on this structure, we also develop an efficient decoding algorithm for the proposed rate-matching deep polar codes by leveraging soft-output successive cancellation list decoding. Furthermore, we provide a decoding error probability analysis that serves as a foundation for the proposed rate-matching code design algorithms. Extensive simulations confirm that the proposed rate-matching deep polar codes provide notable coding gains, particularly at higher code rates.

Recent progress in Large Vision-Language Models (LVLMs) has enabled promising applications in medical tasks, such as report generation and visual question answering. However, existing benchmarks focus mainly on the final diagnostic answer, offering limited insight into whether models engage in clinically meaningful reasoning. To address this, we present CheXStruct and CXReasonBench, a structured pipeline and benchmark built on the publicly available MIMIC-CXR-JPG dataset. CheXStruct automatically derives a sequence of intermediate reasoning steps directly from chest X-rays, such as segmenting anatomical regions, deriving anatomical landmarks and diagnostic measurements, computing diagnostic indices, and applying clinical thresholds. CXReasonBench leverages this pipeline to evaluate whether models can perform clinically valid reasoning steps and to what extent they can learn from structured guidance, enabling fine-grained and transparent assessment of diagnostic reasoning.The benchmark comprises 18,988 QA pairs across 12 diagnostic tasks and 1,200 cases, each paired with up to 4 visual inputs, and supports multi-path, multi-stage evaluation including visual grounding via anatomical region selection and diagnostic measurements.Even the strongest of 12 evaluated LVLMs struggle with structured reasoning and generalization, often failing to link abstract knowledge with anatomically grounded visual interpretation. The code is available at https://github.com/ttumyche/CXReasonBench

Deep polar codes, which employ multi-layered polar kernel pre-transforms in series, are recently introduced variants of pre-transformed polar codes. These codes can reduce the number of minimum-weight codewords, thus closely achieving finite-block length capacity with successive cancellation list (SCL) decoders in certain scenarios. However, for low-latency applications requiring small SCL decoder list sizes, reducing minimum-weight codewords doesn’t necessarily improve decoding performance. To address this limitation, we propose an alternative pre-transform technique to enhance the suitability of polar codes for SCL decoders with practical list sizes. Leveraging the fact that the SCL decoding error event set can be decomposed into two exclusive error event sets, our approach applies two different types of pre-transformations, each targeting the reduction of one of the two error event sets. Extensive simulation results across various block lengths and code rates demonstrate that our codes consistently outperform existing state-of-the-art pre-transformed polar codes, including CRC-aided polar codes and polarization-adjusted convolutional codes, when decoded using SCL decoders with small list sizes.

Nonlinear self-interference cancellation (SIC) techniques are essential for enabling full-duplex communication systems, which can offer spectral efficiencies twice that of traditional half-duplex systems. The challenge of nonlinear SIC is similar to the classic problem of system identification in adaptive filter theory, whose crux lies in constructing the optimal nonlinear basis functions of a nonlinear system. This becomes especially difficult when the system input has a non-stationary distribution, as is the case in practical wireless systems. In this paper, we propose a novel algorithm for nonlinear digital SIC that adaptively constructs orthonormal polynomial basis functions according to the non-stationary moments of the transmit signal. By combining these basis functions with the least mean squares (LMS) algorithm, we introduce a new SIC technique, called the adaptive orthonormal polynomial LMS (AOP-LMS) algorithm. To reduce computational complexity for practical systems, we augment our approach with a precomputed look-up table, which maps a given modulation and coding scheme to its corresponding basis functions. Numerical simulation indicates that our proposed method surpasses existing state-of-the-art SIC algorithms in terms of convergence speed and mean squared error when the transmit signal is non-stationary, such as with adaptive modulation and coding. Experimental evaluation with a wireless testbed further confirms that our proposed approach outperforms existing digital SIC algorithms in practical systems.

Polar codes are the first explicitly constructed error-correcting codes over binary input memoryless channels that achieve provably asymptotic capacity using low-complexity encoding and decoding. Applying upper-triangular pre-transform before polar encoding improves the distance property of the existing polar codes. Although it is known that well-designed pre-transformed polar codes can achieve the normal approximation bound in finite-blocklength regime, achieving that limit requires huge decoding latency, which is undesirable in practical communication system. In this paper, we adopt sparsely applied pre-transform to enhance the weight spectrum of codewords and be decodable under successive cancellation list decoder with small list size. We also propose an algorithm for selecting indices to which pre-transforms are applied. Simulation results confirm that proposed codes surpass 5G standard polar codes with cyclic redundancy check precoding by supporting the effectiveness of sparse pre-transform.

In this paper, we introduce a novel class of pre-transformed polar codes, termed asdeep polar codes. We first present a deep polar encoder that harnesses a series of multi-layered polar transformations with varying sizes. Our approach to encoding enables a low-complexity implementation while significantly enhancing the weight distribution of the code. Moreover, our encoding method offers flexibility in rate-profiling, embracing a wide range of code rates and blocklengths. Next, we put forth a low-complexity decoding algorithm called successive cancellation list withbackpropagation parity checks(SCL-BPC). This decoding algorithm leverages the parity check equations in the reverse process of the multi-layered pre-transformed encoding for SCL decoding. Additionally, we present a low-latency decoding algorithm that employs parallel SCL decoding by treating partially pre-transformed bit patterns as additional frozen bits. Through simulations, we demonstrate that deep polar codes outperform existing pre-transformed polar codes in terms of block error rates across various code rates under short block lengths, while maintaining low encoding and decoding complexity. Furthermore, we show that concatenating deep polar codes with cyclic-redundancy-check codes can achieve the meta-converse bound of the finite block length capacity within 0.4 dB in some instances.