arXiv subjects

Jinho Choi

Publications and source records attributed to Jinho Choi.

At least 19 recordsLinked to original sources

arXiv2026

Rethinking the Foundations of Two-Sided AI Models for 6G

For next-generation air interfaces, two-sided artificial intelligence (AI) models have received growing attention, with AI models deployed at both the transmitter and receiver for efficient channel feedback and data communication. However, their practical deployment is complicated by assumptions commonly made in existing studies, including isolation from legacy users, training under predefined channel conditions, and gradient-based fine-tuning requiring substantial cross-vendor communication. This article revisits these assumptions and presents practical alternatives. First, for legacy coexistence, we integrate two-sided model processing into the 5G New Radio (NR) protocol stack and validate its operation alongside conventional NR on a real-world testbed. Second, instead of training under a massive number of predefined channel conditions, we construct a compact model table by jointly optimizing two-sided models with trainable surrogate channels, and select the best model according to the current channel condition to enable channel adaptation with high task performance and low training/storage overhead. Finally, unlike existing fine-tuning that exchanges large gradient vectors containing potentially private model information, we present gradient-free zeroth-order fine-tuning that requires only scalar feedback, facilitating multi-vendor interoperability. Together, these approaches advance the practical deployment of two-sided AI models while highlighting key open challenges.

eess.SP↗

arXiv2026

Joint Laser Inter-Satellite Link Matching and Traffic Flow Routing in LEO Mega-Constellations via Lagrangian Duality

Low Earth orbit (LEO) mega-constellations greatly extend the coverage and resilience of future wireless systems. Within the mega-constellations, laser inter-satellite links (LISLs) enable high-capacity, long-range connectivity. Existing LISL schemes often overlook mechanical limitations of laser communication terminals (LCTs) and non-uniform global traffic profiles caused by uneven user and gateway distributions, leading to suboptimal throughput and underused LCTs/LISLs -- especially when each satellite carries only a few LCTs. This paper investigates the joint optimization of LCT connections and traffic routing to maximize the constellation throughput, considering the realistic LCT mechanics and a snapshot-level spatial traffic profile. We show that the resulting per-snapshot formulation is a mixed-integer program coupling LCT connections with flow-rate variables under link capacity constraints, and the associated fixed-snapshot abstract decision problem is NP-hard. Due to its intractability, we resort to relaxing the coupling constraints via Lagrangian duality, decomposing the problem into a weighted graph-matching for LCT connections, weighted shortest-path routing tasks, and a linear program for rate allocation. Here, Lagrange multipliers reflect congestion weights between satellites, jointly guiding the matching, routing, and rate allocation. Subgradient descent optimizes the multipliers, with proven convergence. Simulations using real-world constellation and terrestrial data show that our methods substantially improve network throughput by up to $35\%$--$145\%$ over existing non-joint approaches.

eess.SP↗

arXiv2026

A Resource Estimation Model for the Hardware-Software Co-Design of Distributed Quantum Architectures

In distributed quantum computing (DQC), executing monolithic quantum circuits across multiple interconnected quantum processing units (QPUs) requires dedicated communication qubits to generate and distribute entanglement. Because the number of physical qubits within a QPU is finite, a trade-off emerges where allocating more communication qubits increases the capacity of quantum channels for concurrent non-local operations, but reduces the number of computational qubits available for local gate operations. Distributed quantum compilation routinely ignores this channel capacity, while hardware architects lack a method to determine it prior to quantum circuit partitioning. Moreover, scheduling entanglement on demand introduces severe latency, whereas pre-fetching exposes stored pairs to decoherence. We propose an economic order quantity model from perishable inventory theory to optimize the trade-off between entanglement distribution latency and the time cost of decoherence. The resulting estimate is driven by algorithmic demand and physical constraints, offering a dual application for the hardware-software co-design of high-performance DQC: for hardware architects, it gives the optimal allocation of dedicated communication qubits in static heterogeneous architectures; for compiler developers, it gives the optimal number to reserve dynamically in homogeneous architectures.

quant-ph↗

arXiv2026

Mitigating Phase Errors to Improve Signal Quality in RIS-Assisted Satellite Communications

This research presents an advanced framework designed to enhance the received power in satellite-to-Earth communications by utilizing Reconfigurable Intelligent Surfaces (RIS) and focuses on mitigating phase errors arising from hardware imperfections associated with RIS systems. A comprehensive analysis of the phase errors arising from these imperfections is conducted, leading to the development of a robust analytical model that quantitatively incorporates these errors into the assessment of received power evaluations. Subsequently, we propose a methodology to selectively exclude RIS elements that are prone to errors, thereby improving the phase alignment of the received signal and enhancing overall system efficiency. While this strategy leads to a marginal decrease in received power, Bayesian Optimization (BO) is employed to optimize the RIS configuration, maintaining the desired power levels and ensuring signal integrity. The research also delves into the complexities introduced by shadowing effects combined with phase errors. To address these compounded challenges, a decision-making framework utilizing targeted BO is introduced to dynamically optimize RIS configurations, thereby enhancing system robustness and performance under adverse operational conditions. Numerical simulations validate the framework's efficacy in adaptively managing RIS elements, ensuring robust signal integrity and improved reception despite variations stemming from environmental and hardware factors. By addressing critical challenges in RIS-augmented satellite communications, this work highlights the transformative potential of adaptive optimization strategies in advancing the reliability and efficiency of next-generation wireless networks.

eess.SP↗

arXiv2026

Performance Evaluation of High Power Microwave Systems Against UAVs A Probabilistic Antenna Propagation Framework with Sensitivity Analysis

We present an uncertainty-aware probabilistic framework for high-power microwave (HPM) counter-UAV performance under stochastic target motion, beam-pointing uncertainty, atmospheric propagation, and uncertain target susceptibility. It couples stochastic UAV kinematics, a jitter-to-gain model, free-space spreading, gaseous absorption, and rain attenuation, and a logistic energy--response model to derive closed-form statistics of received pulse energy and per-pulse and cumulative effectiveness probabilities. Slant-range variability arises from integrated acceleration noise. Received pulse energy is treated as a target-level exposure metric rather than the exact energy absorbed by an internal component. Closed-form moments and a log-normal approximation yield the mean per-pulse probability through Gaussian--Hermite quadrature and a dwell-time expression under an independent-pulse assumption. Analytical predictions closely match Monte Carlo results under matched assumptions. For a vulnerable-target threshold of $E_{\mathrm{th}}=10^{-2}\,\mathrm{J}$, the model predicts $\bar{P}_{\mathrm{kill}}\gtrsim0.4$ per pulse and $P_{\mathrm{kill,tot}}>99\%$ within about $0.1\,\mathrm{s}$ at kilohertz PRF. For a hardened target with $E_{\mathrm{th}}=10^{-1}\,\mathrm{J}$, it predicts $\bar{P}_{\mathrm{kill}}\approx2.2\times10^{-4}$ ($\approx0.02\%$) and $P_{\mathrm{kill,tot}}\approx20\%$ after $1\,\mathrm{s}$ at $1\,\mathrm{kHz}$ under the i.i.d. pulse assumption. Elasticity analysis identifies slant range as dominant ($S_{\bar{R}}\approx-2$), followed by aperture diameter and transmit power; pointing jitter and atmospheric variability are less influential in the evaluated regimes. Within its assumptions, the framework supports system sizing, trade-off analysis, and risk-aware mission planning.

eess.SP↗

arXiv2026

SIG-SDP: Sparse Interference Graph-Aided Semidefinite Programming for Large-Scale Wireless Time-Sensitive Networking

Wireless time-sensitive networking (WTSN) is essential for Industrial Internet of Things. We address the problem of minimizing time slots needed for WTSN transmissions while ensuring reliability subject to interference constraints -- an NP-hard task. Existing semidefinite programming (SDP) methods can relax and solve the problem but suffer from high polynomial complexity. We propose a sparse interference graph-aided SDP (SIG-SDP) framework that exploits the interference's sparsity arising from attenuated signals between distant user pairs. First, the framework utilizes the sparsity to establish the upper and lower bounds of the minimum number of slots and uses binary search to locate the minimum within the bounds. Here, for each searched slot number, the framework optimizes a positive semidefinite (PSD) matrix indicating how likely user pairs share the same slot, and the constraint feasibility with the optimized PSD matrix further refines the slot search range. Second, the framework designs a matrix multiplicative weights (MMW) algorithm that accelerates the optimization, achieved by only sparsely adjusting interfering user pairs' elements in the PSD matrix while skipping the non-interfering pairs. We also design an online architecture to deploy the framework to adjust slot assignments based on real-time interference measurements. Simulations show that the SIG-SDP framework converges in near-linear complexity and is highly scalable to large networks. The framework minimizes the number of slots with up to 10 times faster computation and up to 100 times lower packet loss rates than compared methods. The online architecture demonstrates how the algorithm complexity impacts dynamic networks' performance.

eess.SP↗

arXiv2026

Scalable Interference Graph Learning for Low-Latency Wi-Fi Networks using Hashing-based Evolution Strategy

Wi-Fi 7 introduces the restricted target wake time (RTWT) mechanism, which is vital for Industrial IoT (IIoT) applications requiring periodic, reliable, and low-latency communication. RTWT enables deterministic channel access by assigning scheduled transmission slots to stations (STAs), minimizing contention and interference. However, determining efficient RTWT slot assignments remains challenging in dense networks, where conventional interference graph-based models lack flexibility and scalability. To overcome this, we propose a scalable interference graph learning (IGL) framework that learns optimal interference graph representations for graph coloring-based RTWT scheduling. The IGL leverages an evolution strategy (ES) to train a neural network (NN) using a single network-wide reward, avoiding costly edge-wise feedback. Furthermore, a deep hashing function (DHF) groups interfering STAs, limiting training and inference to relevant subsets and greatly reducing complexity. Simulation results demonstrate that the proposed IGL improves slot efficiency by up to 25\%, reduces packet losses by up to 30\% in dynamic environments. Thanks to DHF, it also reduces the training and inference time of IGL by 4 and 8 times, respectively, and the online slot assignment time by 3 times in large networks.

eess.SP↗

arXiv2026

Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission

To support emerging language-based applications using dispersed and heterogeneous computing resources, the hybrid language model (HLM) offers a promising architecture, where an on-device small language model (SLM) generates draft tokens that are validated and corrected by a remote large language model (LLM). However, the original HLM suffers from substantial communication overhead, as the LLM requires the SLM to upload the full vocabulary distribution for each token. Moreover, both communication and computation resources are wasted when the LLM validates tokens that are highly likely to be accepted. To overcome these limitations, we propose communication-efficient and uncertainty-aware HLM (CU-HLM). In CU-HLM, the SLM transmits truncated vocabulary distributions only when its output uncertainty is high. We validate the feasibility of this opportunistic transmission by discovering a strong correlation between SLM's uncertainty and LLM's rejection probability. Furthermore, we theoretically derive optimal uncertainty thresholds and optimal vocabulary truncation strategies. Simulation results show that, compared to standard HLM, CU-HLM achieves up to 206$\times$ higher token throughput by skipping 74.8% transmissions with 97.4% vocabulary compression, while maintaining 97.4% accuracy.

cs.DC↗

arXiv2026

Context-Aware Wireless Token Communication via Joint Token Masking and Detection

The increasing use of token-based representations in language-driven applications has motivated wireless token communication, where tokens are treated as fundamental units for transmission. However, conventional communication systems overlook dependencies among tokens and allocate transmission resources uniformly, leading to inefficient use of limited wireless resources under channel impairments. In this paper, we propose a context-aware token communication framework that leverages a masked language model (MLM) as a shared contextual model between the transmitter (Tx) and receiver (Rx). At the Rx, we develop a context-aware token detection method that integrates channel likelihoods with MLM-based contextual priors under a Bayesian formulation, enabling robust token inference over noisy channels. At the Tx, we propose a context-aware token masking strategy that selectively omits tokens that can be reliably inferred at the Rx, allowing the available power budget to be concentrated on more informative tokens. These components are jointly designed through a shared MLM, establishing a unified Tx-Rx framework for efficient token transmission and detection. Simulation results demonstrate that the proposed framework significantly improves reconstruction performance compared to conventional and existing token communication schemes, achieving up to 1.77X and 1.63X performance gains on the Europarl corpus and WikiText-103 datasets, respectively.

eess.SP↗

arXiv2026

Toward Scalable SDN for LEO Mega-Constellations: A Graph Learning Approach

Terrestrial network limitations drive the integration of non-terrestrial networks (NTNs), notably mega-constellations comprising thousands of low Earth orbit (LEO) satellites. While these satellites act as interconnected network switches via inter-satellite links (ISLs), their massive scale creates severe bottlenecks for network management. To address this, we propose a scalable, hierarchical software-defined networking (SDN) framework. Our architecture leverages graph neural networks (GNNs) to compactly represent the constellation topology, and Koopman theory to linearize nonlinear dynamics. Specifically, a Graph Koopman Autoencoder (GKAE) forecasts spatio-temporal behavior within a linear subspace for each orbital shell. A central SDN controller then aggregates these shell-level predictions for globally coordinated control. Simulations on the Starlink constellation demonstrate that our approach achieves at least a 42.8\% improvement in spatial compression and a 10.81\% improvement in temporal forecasting compared to established baselines, all while utilizing a significantly smaller model footprint.

cs.LG↗

arXiv2026

Towards Optimal Semantic Communications: Reconsidering the Role of Semantic Feature Channels

This paper investigates the optimization of transmitting the encoder outputs, termed semantic features (SFs), in semantic communication (SC). We begin by modeling the entire communication process from the encoder output to the decoder input, encompassing the physical channel and all transceiver operations, as the SF channel, thereby establishing an encoder-SF channel-decoder pipeline. In contrast to prior studies that assume a fixed SF channel, we note that the SF channel is configurable, as its characteristics are shaped by various transmission and reception strategies, such as power allocation. Based on this observation, we formulate the SF channel optimization problem under a mutual information constraint between the SFs and their reconstructions, and analytically derive the optimal SF channel under a linear encoder-decoder structure and Gaussian source assumption. Building on this analysis, we propose a joint optimization framework for the encoder-decoder and SF channel applicable to both analog and digital SC systems. To realize the optimized SF channel, we also propose a physical-layer calibration strategy that enables real-time power control and adaptation to varying channel conditions. Simulation results demonstrate that the proposed SF channel optimization achieves superior task performance under various communication environments.

eess.SP↗

arXiv2026

Blockage-Aware and Shadowing Aware RIS Assisted Joint Communication and Positioning for Urban Non Terrestrial Networks

Reconfigurable intelligent surfaces (RISs) have recently attracted interest for non-terrestrial networks (NTNs), especially for improving satellite communication performance. However, RIS-assisted urban NTN designs that jointly support reliable communication and user positioning under blockage, while maintaining low online complexity, remain limited. This paper proposes a blockage-aware and shadowing-aware RIS-assisted framework for joint communication and positioning in an urban low-Earth-orbit (LEO) satellite downlink. A terrestrial RIS is used both to reinforce the blockage-sensitive satellite--user link and to create an additional reflected path that enhances delay-domain positioning observability. We develop a reduced two-dimensional positioning model based on the direct-path delay and the RIS-assisted excess delay, and combine the resulting position error bound (PEB) with the received signal-to-noise ratio (SNR) into a unified utility. A blockage-aware three-mode policy then adapts RIS operation among communication-oriented, balanced, and positioning-oriented modes according to the direct-link condition. To improve robustness, spatially correlated RIS--user shadowing is tracked across coherence blocks using a state-space model and a scalar Kalman filter, and the filtered estimate is used in a robust codebook-based RIS selection strategy with low online complexity. Numerical results show that the proposed framework provides a controllable SNR--PEB tradeoff, improves positioning accuracy while maintaining competitive SNR, stabilizes codeword selection under shadowing uncertainty, and increases joint success probability with RIS size and phase resolution, with diminishing returns at high hardware complexity.

eess.SP↗

arXiv2026

Training-Free Multi-User Generative Semantic Communications via Null-Space Diffusion Sampling

In recent years, novel communication strategies have emerged to face the challenges that the increased number of connected devices and the higher quality of transmitted information are posing. Among them, semantic communication obtained promising results especially when combined with state-of-the-art deep generative models, such as large language or diffusion models, able to regenerate content from extremely compressed semantic information. However, most of these approaches focus on single-user scenarios processing the received content at the receiver on top of conventional communication systems. In this paper, we propose to go beyond these methods by developing a novel generative semantic communication framework tailored for multi-user scenarios. This system assigns the channel to users knowing that the lost information can be filled in with a diffusion model at the receivers. Under this innovative perspective, OFDMA systems should not aim to transmit the largest part of information, but solely the bits necessary to the generative model to semantically regenerate the missing ones. The thorough experimental evaluation shows the capabilities of the novel diffusion model and the effectiveness of the proposed framework, leading towards a GenAI-based next generation of communications.

eess.SP↗

arXiv2026

VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models

High-performing vision language models still produce incorrect answers, yet their failure modes are often difficult to explain. To make model internals more accessible and enable systematic debugging, we introduce VisualScratchpad, an interactive interface for visual concept analysis during inference. We apply sparse autoencoders to the vision encoder and link the resulting visual concepts to text tokens via text-to-image attention, allowing us to examine which visual concepts are both captured by the vision encoder and utilized by the language model. VisualScratchpad also provides a token-latent heatmap view that suggests a sufficient set of latents for effective concept ablation in causal analysis. Through case studies, we reveal three underexplored failure modes: limited cross-modal alignment, misleading visual concepts, and unused hidden cues. Project page: https://hyesulim.github.io/visual_scratchpad_projectpage/

cs.AI↗

arXiv2026

Efficient Time-Aware Partitioning of Quantum Circuits for Distributed Quantum Computing

To overcome the physical limitations of scaling monolithic quantum computers, distributed quantum computing (DQC) interconnects multiple smaller-scale quantum processing units (QPUs) to form a quantum network. However, this approach introduces a critical challenge, namely the high cost of quantum communication between remote QPUs incurred by quantum state teleportation and quantum gate teleportation. To minimize this communication overhead, DQC compilers must strategically partition quantum circuits by mapping logical qubits to distributed physical QPUs. Static graph partitioning methods are fundamentally ill-equipped for this task as they ignore execution dynamics and underlying network topology, while metaheuristics require substantial computational runtime. In this work, we propose a heuristic based on beam search to solve the circuit partitioning problem. Our time-aware algorithm incrementally constructs a low-cost sequence of qubit assignments across successive time steps to minimize overall communication overhead. The time and space complexities of the proposed algorithm scale quadratically with the number of qubits and linearly with circuit depth, offering a significant computational speedup over common metaheuristics. We demonstrate that our proposed algorithm consistently achieves significantly lower communication costs than static baselines across varying circuit sizes, depths, and network topologies, providing an efficient compilation tool for near-term distributed quantum hardware.

quant-ph↗

arXiv2026

Stochastic Design of Active RIS-Assisted Satellite Downlinks under Interference, Folded Noise, and EIRP Constraints

Active reconfigurable intelligent surfaces (RISs) can mitigate the double-fading loss of passive reflection in satellite downlinks. However, their gains are limited by random co-channel interference, gain-dependent amplifier noise, and regulatory emission constraints. This paper develops a stochastic reliability framework for active RIS-assisted satellite downlinks by modeling the desired and interfering channels, receiver noise, and RIS amplifier noise as random variables. The resulting instantaneous signal-to-interference-plus-noise ratio (SINR) model explicitly captures folded cascaded amplifier noise and reveals a finite high-gain SINR ceiling. To guarantee a target outage level, we formulate a chance-constrained max-SINR design that jointly optimizes the binary RIS configuration and a common amplification gain. The chance constraint is handled using a sample-average approximation (SAA) with a violation budget. The resulting feasibility problem is solved as a mixed-integer second-order cone program (MISOCP) within a bisection search over the SINR threshold. Practical implementation is enforced by restricting the gain to an admissible range determined by small-signal stability and effective isotropic radiated power (EIRP) limits. We also derive realization-wise SINR envelopes based on eigenvalue and l1-norm bounds, which provide interpretable performance limits and fast diagnostics. Monte Carlo results show that these envelopes tightly bound the simulated SINR, reproduce the predicted saturation behavior, and quantify performance degradation as interference increases. Overall, the paper provides a solver-ready, reliability-targeting design methodology whose achieved reliability is validated through out-of-sample Monte Carlo testing under realistic randomness and hardware constraints.

eess.SP↗

arXiv2026

Duality-Guided Graph Learning for Real-Time Joint Connectivity and Routing in LEO Mega-Constellations

Laser inter-satellite links (LISLs) of low Earth orbit (LEO) mega-constellations enable high-capacity backbone connectivity in non-terrestrial networks, but their management is challenged by limited laser communication terminals, mechanical pointing constraints, and rapidly time-varying network topologies. This paper studies the joint problem of LISL connection establishment, traffic routing, and flow-rate allocation under heterogeneous global traffic demand and gateway availability. We formulate the problem as a mixed-integer optimization over large-scale, time-varying constellation graphs and develop a Lagrangian dual decomposition that interprets per-link dual variables as congestion prices coordinating connectivity and routing decisions. To overcome the prohibitive latency of iterative dual updates, we propose DeepLaDu, a Lagrangian duality-guided deep learning framework that trains a graph neural network (GNN) to directly infer per-link (edge-level) congestion prices from the constellation state in a single forward pass. We enable scalable and stable training using a subgradient-based edge-level loss in DeepLaDu. We analyze the convergence and computational complexity of the proposed approach and evaluate it using realistic Starlink-like constellations with optical and traffic constraints. Simulation results show that DeepLaDu achieves up to 20\% higher network throughput than non-joint or heuristic baselines, while matching the performance of iterative dual optimization with orders-of-magnitude lower computation time, suitable for real-time operation in dynamic LEO networks.

eess.SP↗

arXiv2026

Context-Aware Iterative Token Detection and Masked Transmission for Wireless Token Communication

The success of large-scale language models has established tokens as compact and meaningful units for natural-language representation, which motivates token communication over wireless channels, where tokens are considered fundamental units for wireless transmission. We propose a context-aware token communication framework that uses a pretrained masked language model (MLM) as a shared contextual probability model between the transmitter (Tx) and receiver (Rx). At Rx, we develop an iterative token detection method that jointly exploits MLM-guided contextual priors and channel observations based on a Bayesian perspective. At Tx, we additionally introduce a context-aware masking strategy which skips highly predictable token transmission to reduce transmission rate. Simulation results demonstrate that the proposed framework substantially improves reconstructed sentence quality and supports effective rate adaptation under various channel conditions.

eess.SP↗