arXiv subjects

Sojeong Park

Publications and source records attributed to Sojeong Park.

12 recordsLinked to original sources

arXiv2026

Prediction-Aided V2X Safety Message Recovery via Uncertainty-Aware LDPC Decoding

Periodic basic safety messages (BSMs) exhibit temporal correlation as vehicle motion evolves continuously over time. This temporal structure provides predictive information about the current BSM and motivates prediction-aided recovery after a decoding failure. For low-density parity-check (LDPC)-coded transmission, a straightforward approach maps a predicted vehicle state to a candidate bit sequence and uses it as decoder prior information. However, a point prediction does not capture the uncertainty of the prediction. The resulting hard point prior assigns fixed confidence to each predicted bit and may introduce strong erroneous evidence when the prediction is incorrect. This paper proposes an uncertainty-aware prediction-aided LDPC recovery framework for vehicle-to-everything (V2X) safety messages. Instead of using a deterministic point prediction, the proposed method represents the current vehicle state by a predictive distribution. The distribution is propagated through BSM field quantization and serialization to obtain bit-level probabilities, which are converted into prior log-likelihood ratios (LLRs) whose magnitudes reflect prediction reliability. After an initial cyclic redundancy check (CRC) failure, these probabilistic priors are combined with the original channel observations and used in a second LDPC decoding pass. The proposed method preserves the standardized message representation and channel-coding procedure. Simulation results show that the proposed probabilistic priors outperform the hard point prior across different motion predictors. At $E_b/N_0=0.75$~dB, the proposed method recovers 87.27% of the messages that fail the initial decoding attempt.

eess.SP↗

arXiv2026

LLM-Assisted LDPC Decoding via Syndrome-Verified Semantic Priors

Semantic communication exploits the meaning of the payload, which bit-level processing discards. When channel decoding fails on a natural language payload, the errors appear as corrupted characters in the recovered text. A large language model (LLM) infers the intended characters from the semantic context, but it can also produce incorrect corrections. Applying them directly introduces new bit errors when the LLM modifies characters incorrectly. In this paper, we propose an LLM-assisted decoding framework for low-density parity-check (LDPC) codes. Rather than trusting LLM predictions, the decoder evaluates the modified characters jointly against the parity-check constraints and admits only the accepted corrections as verified semantic priors. These priors are injected as soft updates to the channel log-likelihood ratios, preserving the original channel evidence without modifying the decoder. A subsequent belief propagation pass distributes the injected evidence across the check nodes, recovering not only the injected bits but also the residual errors that the LLM fails to correct. Simulations demonstrate a 73% bit error rate reduction over a conventional decoder at 2.0 dB, whereas doubling its iterations to the same budget yields only 21%. The verification maintains an injection precision above 0.88 despite inaccurate LLM predictions, demonstrating that semantic knowledge can be reliably translated into physical-layer reliability gains.

eess.SP↗

arXiv2026

SceneBaker: Radio-Ready Scene Generation for Sionna Ray-Tracing

Wireless digital-twin (DT) research needs ray-tracing (RT) scenes that can be generated, versioned, and checked reproducibly. Current visual-authoring workflows can produce plausible city models, but they are poorly matched to repeated radio-simulation studies because geometry, terrain contact, and material semantics often require manual repair after export. This paper presents SceneBaker, a programmatic scene-generation pipeline that turns map and terrain data into Sionna RT-ready Mitsuba scenes without a GUI authoring step. Across four campus scenes, SceneBaker generates Sionna RT-ready scenes over the same geographic bounds as a Blender-generated baseline. The generated scenes avoid representative building-generation and terrain-contact faults while preserving comparable coverage-field and link-level channel-response behavior. The implementation and generated comparison assets are available at https://github.com/hslyu/sionna-scene-baker.

eess.SP↗

arXiv2026

Temporal Channel Estimation for Generalized CSI Feedback

Efficient Channel State Information (CSI) feedback is indispensable for frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) systems. Existing compressed sensing (CS) algorithms exploit delay-domain sparsity but suffer from prohibitive iterative latency and discrete grid mismatch. Conversely, deep learning (DL) approaches achieve rapid inference but lack spatial scalability and domain adaptability, failing to generalize to unseen propagation environments, and demand computationally heavy encoders and decoder. In this paper, we propose TAP, a Tap-Assisted Parametric CSI Compression. TAP is a one-shot neural framework that unifies the speed of DL with the mathematical interpretability of CS. TAP replaces iterative pursuit with a lightweight 1D neural network that extracts dominant continuous propagation delays from temporal channel sequences via a differentiable sub-grid interpolation operator. TAP achieves true architecture independence, enabling zero-shot generalization across diverse array geometries and unseen propagation environments. Furthermore, TAP yields a completely decoder-free payload, allowing the BS to reconstruct the channel via a simple inverse fast Fourier transform (IFFT). Extensive evaluations across five 3GPP environments demonstrate that TAP achieves a 3.13 to 12.22 dB channel frequency response normalized mean square error (CFR-NMSE) improvement over CsiNet while shrinking the model footprint by 660 times to under 1 MB. Operating with sub-millisecond latencies, TAP accelerates inference by 2700 times over classical iterative OMP, providing a scalable and deployment-ready solution for next-generation networks.

eess.SP↗

arXiv2026

Matrix product state approach to lossy boson sampling and noisy IQP sampling

Sampling problems have emerged as a central avenue for demonstrating quantum advantage on noisy intermediate-scale quantum devices. However, physical noise can fundamentally alter their computational complexity, often making them classically tractable. Motivated by the recent success of matrix product state (MPS)-based classical simulation of Gaussian boson sampling (Oh et al., 2024), we extend this framework to investigate the classical simulability of other noisy quantum sampling models. We develop MPS-based classical algorithms for lossy boson sampling and noisy instantaneous quantum polynomial-time (IQP) sampling, both of which retain the tunable accuracy characteristic of the MPS approach through the bond dimension. Our approach constructs pure-state decompositions of noisy or lossy input states whose components remain weakly entangled after circuit evolution, thereby providing a means to systematically explore the boundary between quantum-hard and classically-simulable regimes. For boson sampling, we analyze single-photon, Fock, and cat-state inputs, showing that classical simulability emerges at transmission rates scaling as $O(1/\sqrt{N})$, reaching the known boundary of quantum advantage with a tunable and scalable method. Beyond reproducing previous thresholds, our algorithm offers significantly improved control over the accuracy-efficiency trade-off. It further extends the applicability of MPS-based simulation to broader classes of noisy quantum sampling models, including IQP circuits.

quant-ph↗

arXiv2026

Semantic-Aware Data-Aided Channel Estimation with Large Language Models for MIMO Systems

Data-aided channel estimation enhances spectral efficiency by reusing detected symbols as virtual pilots. In this process, selecting only reliable symbols is crucial to prevent misdetected symbols from corrupting the channel estimate. However, conventional methods rely exclusively on physical-layer statistics. Beyond physical-layer information, transmitted payloads possess inherent semantic structures that can be exploited to resolve detection errors. In this paper, we propose a novel semantic-aware channel estimation framework for multiple-input multiple-output (MIMO) systems that utilizes a fine-tuned large language model (LLM) to perform reliable symbol selection and correction based on semantic information. The framework employs a two-layer mechanism: one layer selects reliable decoded symbols through semantic verification, while the other selects accurately LLM-corrected symbols by cross-validating them against the received signal using physical-layer information. We prove that corrected symbols yield a strictly larger expected reduction in estimation error than initially correctly decoded symbols. Extensive simulations demonstrate that the proposed framework significantly outperforms conventional data-aided schemes in both normalized mean squared error and bit error rate, closely approaching the performance of an oracle estimator.

eess.SP↗

arXiv2026

Semantic Pilot Design for Data-Aided Channel Estimation Using a Large Language Model

This paper proposes a semantic pilot design for data-aided channel estimation in text-inclusive data transmission, using a large language model (LLM). In this scenario, channel impairments often appear as typographical errors in the decoded text, which can be corrected using an LLM. The proposed method compares the initially decoded text with the LLM-corrected version to identify reliable decoded symbols. A set of selected symbols, referred to as a semantic pilot, is used as an additional pilot for data-aided channel estimation. To the best of our knowledge, this work is the first to leverage semantic information for reliable symbol selection. Simulation results demonstrate that the proposed scheme outperforms conventional pilot-only estimation, achieving lower normalized mean squared error and phase error of the estimated channel, as well as reduced bit error rate.

eess.SP↗

arXiv2026

Classical simulation of a quantum circuit with noisy magic inputs

Magic states are essential for universal quantum computation and are widely viewed as a key source of quantum advantage, yet in realistic devices they are inevitably noisy. In this work, we characterize how noise on injected magic resources changes the classical simulability of quantum circuits and when it induces a transition from classically intractable behavior to efficient classical simulation. We adopt a resource-centric noise model in which only the injected magic components are noisy, while the baseline states, operations, and measurements belong to an efficiently simulable family. Within this setting, we develop an approximate classical sampling algorithm with controlled error and prove explicit noise-dependent conditions under which the algorithm runs in polynomial time. Our framework applies to both qubit circuits with Clifford baselines and fermionic circuits with matchgate baselines, covering representative noise channels such as dephasing and particle loss. We complement the analysis with numerical estimates of the simulation cost, providing concrete thresholds and runtime scaling across practically relevant parameter regimes.

quant-ph↗

arXiv2026

User-Centric Stream Sensing for Grant-Free Access: Deep Learning with Covariance Differencing

Grant-free (GF) access is essential for massive connectivity but faces collision risks due to uncoordinated transmissions. While user-side sensing can mitigate these collisions by enabling autonomous transmission decisions, conventional methods become ineffective in overloaded scenarios where active streams exceed receive antennas. To address this problem, we propose a differential stream sensing framework that reframes the problem from estimating the total stream count to isolating newly activated streams via covariance differencing. We analyze the covariance deviation induced by channel variations to establish a theoretical bound based on channel correlation for determining the sensing window size. To mitigate residual interference from finite sampling, a deep learning (DL) classifier is integrated. Simulations across both independent and identically distributed flat Rayleigh fading and standardized channel environments demonstrate that the proposed method consistently outperforms non-DL baselines and remains robust in overloaded scenarios.

eess.SP↗

arXiv2025

Robust Transmission of Punctured Text with Large Language Model-based Recovery

With the recent advancements in deep learning, semantic communication which transmits only task-oriented features, has rapidly emerged. However, since feature extraction relies on learning-based models, its performance fundamentally depends on the training dataset or tasks. For practical scenarios, it is essential to design a model that demonstrates robust performance regardless of dataset or tasks. In this correspondence, we propose a novel text transmission model that selects and transmits only a few characters and recovers the missing characters at the receiver using a large language model (LLM). Additionally, we propose a novel importance character extractor (ICE), which selects transmitted characters to enhance LLM recovery performance. Simulations demonstrate that the proposed filter selection by ICE outperforms random filter selection, which selects transmitted characters randomly. Moreover, the proposed model exhibits robust performance across different datasets and tasks and outperforms traditional bit-based communication in low signal-to-noise ratio conditions.

eess.SP↗

arXiv2023

Do All Asians Look the Same?: A Comparative Analysis of the East Asian Facial Color Desires using Instagram

Selfies represent people's desires, and social media platforms like Instagram have been flooded with them. This study uses selfie data to examine how peoples' desires for ideal facial representations vary by region, particularly in East Asia. Through the analysis, we aim to refute the "all Asians prefer identical visuals," which is a subset of the prevalent Western belief that "all Asians look the same." Our findings, reinforced by postcolonial interpretations, dispute those assumptions. We propose a strategy for resolving the mismatch between real-world desires and the Western beauty market's views. We expect the disparity between hegemonic color schemes and the augmented skin colors shown by our results may facilitate the study of color and Asian identity.

cs.CY↗

arXiv2019

Fence GAN: Towards Better Anomaly Detection

Anomaly detection is a classical problem where the aim is to detect anomalous data that do not belong to the normal data distribution. Current state-of-the-art methods for anomaly detection on complex high-dimensional data are based on the generative adversarial network (GAN). However, the traditional GAN loss is not directly aligned with the anomaly detection objective: it encourages the distribution of the generated samples to overlap with the real data and so the resulting discriminator has been found to be ineffective as an anomaly detector. In this paper, we propose simple modifications to the GAN loss such that the generated samples lie at the boundary of the real data distribution. With our modified GAN loss, our anomaly detection method, called Fence GAN (FGAN), directly uses the discriminator score as an anomaly threshold. Our experimental results using the MNIST, CIFAR10 and KDD99 datasets show that Fence GAN yields the best anomaly classification accuracy compared to state-of-the-art methods.

cs.LG↗