arXiv subjects

Sunwoo Kim

Publications and source records attributed to Sunwoo Kim.

At least 37 records · Page 2Linked to original sources

arXiv2026

Environment-aware Near-field UE Tracking under Partial Blockage and Reflection

This paper proposes an environment-aware near-field (NF) user equipment (UE) tracking method for extremely large aperture arrays. By integrating known surface geometries and tracking the line-of-sight (LOS) and non-line-of-sight (NLOS) indicators per antenna element, the method captures partial blockages and reflections specific to the NF spherical-wavefront regime, which are unavailable under the conventional far-field (FF) assumption. The UE positions are tracked by maximizing the cosine similarity between the predicted and received channels, enabling tracking even under complete LOS obstruction. Simulation results confirm that increasing environment-awareness improves accuracy, and that NF consistently outperforms FF baselines, achieving a $0.22\,\mathrm{m}$ root-mean-square error with full environment-awareness.

eess.SP↗

arXiv2026

Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design

We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design. While diffusion models have proven highly effective in modeling complex, high-dimensional data distributions, real-world applications often demand more than high-fidelity generation, requiring optimization with respect to potentially non-differentiable reward functions such as physics-based simulation or rewards based on scientific knowledge. Although RL methods have been explored to fine-tune diffusion models for such objectives, they often suffer from instability, low sample efficiency, and mode collapse due to their on-policy nature. In this work, we propose an iterative distillation-based fine-tuning framework that enables diffusion models to optimize for arbitrary reward functions. Our method casts the problem as policy distillation: it collects off-policy data during the roll-in phase, simulates reward-based soft-optimal policies during roll-out, and updates the model by minimizing the KL divergence between the simulated soft-optimal policy and the current model policy. Our off-policy formulation, combined with KL divergence minimization, enhances training stability and sample efficiency compared to existing RL-based methods. Empirical results demonstrate the effectiveness and superior reward optimization of our approach across diverse tasks in protein, small molecule, and regulatory DNA design. The source code is released at (https://divelab.github.io/VIDD/).

cs.LG↗

arXiv2026

Personalized Parameter-Efficient Fine-Tuning of Foundation Models for Multimodal Recommendation

In recent years, substantial research has integrated multimodal item metadata into recommender systems, often by using pre-trained multimodal foundation models to encode such data. Since these models are not originally trained for recommendation tasks, recent works efficiently adapt them via parameter-efficient fine-tuning (PEFT). However, even with PEFT, item embeddings from multimodal foundation models remain user-blind: item embeddings are not conditioned on user interests, despite the fact that users with diverse interests attend to different item aspects. To address this limitation, we propose PerPEFT, a personalized PEFT strategy for multimodal recommendation. Specifically, PerPEFT groups users by interest and assigns a distinct PEFT module to each group, enabling each module to capture the fine-grained item aspects most predictive of that group`s purchase decisions. We further introduce a specialized training technique that strengthens this user-group conditioning. Notably, PerPEFT is PEFT-agnostic and can be paired with any PEFT method applicable to multimodal foundation models. Through extensive experiments, we show that (1) PerPEFT outperforms the strongest baseline by up to 15.3% (NDCG@20) and (2) delivers consistent gains across diverse PEFT variants. It is noteworthy that, even with personalization, PEFT remains lightweight, adding only 1.3% of the parameter count of the foundation model. We provide our code and datasets at https://github.com/kswoo97/PerPEFT.

cs.IR↗

arXiv2026

From Pragmas to Partners: A Symbiotic Evolution of Agentic High-Level Synthesis

The rise of large language models has sparked interest in AI-driven hardware design, raising the question: does high-level synthesis (HLS) still matter in the agentic era? We argue that HLS remains essential. While we expect mature agentic hardware systems to leverage both HLS and RTL, this paper focuses on HLS and its role in enabling agentic optimization. HLS offers faster iteration cycles, portability, and design permutability that make it a natural layer for agentic optimization. This position paper makes three contributions. First, we explain why HLS serves as a practical abstraction layer and a golden reference for agentic hardware design. Second, we identify key limitations of current HLS tools, namely inadequate performance feedback, rigid interfaces, and limited debuggability that agents are uniquely positioned to address. Third, we propose a taxonomy for the symbiotic evolution of agentic HLS, clarifying how responsibility shifts from human designers to AI agents as systems advance from copilots to autonomous design partners.

cs.CL↗

arXiv2026

Large Multimodal Model-Aided Scheduling for 6G Autonomous Communications

Recently, large language models (LLMs) have gained significant attention for their ability to generate fast and accurate answer to the given query. These models have evolved into large multimodal models (LMMs), which can interpret and analyze multimodal inputs such as images and text. With the exponential growth of AI functionalities in autonomous devices, the central unit (CU), a digital processing unit performing AI inference, needs to handle LMMs to effectively control these devices. To ensure seamless command delivery to devices, the CU must perform the scheduling, which involves resource block (RB) allocation for data transmission and modulation and coding scheme (MCS) index selection based on the channel conditions. This task is challenging in many practical environments in 6G, where even small user movement can cause abrupt channel changes. In this paper, we propose a novel LMM-based scheduling technique to address this challenge. Our key idea is to leverage LMM to predict future channel parameters (e.g., distance, angles, and path gain) by analyzing the visual sensing information as well as pilot signals. By exploiting LMMs to predict the presence of reliable path and geometric information of users from the visual sensing information, and then combining these with past channel states from pilot signals, we can accurately predict future channel parameters. Using these predictions, we can preemptively make channel-aware scheduling decisions. From the numerical evaluations, we show that the proposed technique achieves more than 30% throughput gain over the conventional scheduling techniques.

cs.IT↗

arXiv2026

System-Level Comparison of Multimodal and In-Band mmWave Sensing for Beam Prediction in 6G ISAC

Integrated sensing and communication (ISAC) can reduce beam-training overhead in mmWave vehicle-to-infrastructure (V2I) links by enabling in-band sensing-based beam prediction, while exteroceptive sensors can further enhance the prediction accuracy. This work develop a system-level framework that evaluates camera, LiDAR, radar, GPS, and in-band mmWave power, both individually and in multimodal fusion using the DeepSense-6G Scenario-33 dataset. A latency-aware neural network composed of lightweight convolutional (CNN) and multilayer-perceptron (MLP) encoders predict a 64-beam index. We assess performance using Top-k accuracy alongside spectral-efficiency (SE) gap, signal-to-noise-ratio (SNR) gap, rate loss, and end-to-end latency. Results show that the mmWave power vector is a strong standalone predictor, and fusing exteroceptive sensors with it preserves high performance: mmWave alone and mmWave+LiDAR/GPS/Radar achieve 98% Top-5 accuracy, while mmWave+camera achieves 94% Top-5 accuracy. The proposed framework establishes calibrated baselines for 6G ISAC-assisted beam prediction in V2I systems.

eess.SP↗

arXiv2025

CNSight: Evaluation of Clinical Note Segmentation Tools

Clinical notes are often stored in unstructured or semi-structured formats after extraction from electronic medical record (EMR) systems, which complicates their use for secondary analysis and downstream clinical applications. Reliable identification of section boundaries is a key step toward structuring these notes, as sections such as history of present illness, medications, and discharge instructions each provide distinct clinical contexts. In this work, we evaluate rule-based baselines, domain-specific transformer models, and large language models for clinical note segmentation using a curated dataset of 1,000 notes from MIMIC-IV. Our experiments show that large API-based models achieve the best overall performance, with GPT-5-mini reaching a best average F1 of 72.4 across sentence-level and freetext segmentation. Lightweight baselines remain competitive on structured sentence-level tasks but falter on unstructured freetext. Our results provide guidance for method selection and lay the groundwork for downstream tasks such as information extraction, cohort identification, and automated summarization.

cs.CL↗

arXiv2025

Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption

Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information from neighboring nodes, is commonly employed to encode node features and graph topology. However, excessive reliance on graph convolution can be suboptimal-especially in non-homophilic graphs-since it may yield unduly similar embeddings for nodes that differ in their features or topological properties. As a result, adjusting the degree of graph convolution usage has been actively explored in supervised learning settings, whereas such approaches remain underexplored in unsupervised scenarios. To tackle this, we propose FUEL, which adaptively learns the adequate degree of graph convolution usage by aiming to enhance intra-class similarity and inter-class separability in the embedding space. Since classes are unknown, FUEL leverages node features to identify node clusters and treats these clusters as proxies for classes. Through extensive experiments using 15 baseline methods and 14 benchmark datasets, we demonstrate the effectiveness of FUEL in downstream tasks, achieving state-of-the-art performance across graphs with diverse levels of homophily.

cs.LG↗

arXiv2025

Blocker-Aware Beamforming and Dynamic Power Allocation for Multicarrier ISAC-NOMA Systems

This paper proposes a blocker-aware multicarrier integrated sensing and communication (ISAC)-non orthogonal multiple access (NOMA) system, leveraging hybrid beamforming and dynamic power allocation to enhance spectrum efficiency in 6G networks. Recognizing the performance degradation caused by environmental blockers, the system introduces a joint waveform design that ensures robust operation under varying channel conditions. A channel switching mechanism is deployed to reroute communication through alternative non-line-of-sight paths when the primary line-of-sight links are obstructed. Moreover, a dynamic power allocation strategy enforces a minimum rate constraint for the weak NOMA user, ensuring consistent quality of service. Extensive simulations over multiple blockage scenarios and signal to noise (SNR) conditions validate the effectiveness of the proposed solution. Notably, under severe blockage, the system achieves up to a 400% sensing rate enhancement at 15 dB SNR, with only a 20% reduction in communication rate. These results corroborate the system's ability to adapt and optimize joint sensing-communication performance in practical deployment environments.

eess.SP↗

arXiv2025

Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement

Test-time scaling through reward-guided generation remains largely unexplored for discrete diffusion models despite its potential as a promising alternative. In this work, we introduce Iterative Reward-Guided Refinement (IterRef), a novel test-time scaling method tailored to discrete diffusion that leverages reward-guided noising-denoising transitions to progressively refine misaligned intermediate states. We formalize this process within a Multiple-Try Metropolis (MTM) framework, proving convergence to the reward-aligned distribution. Unlike prior methods that assume the current state is already aligned with the reward distribution and only guide the subsequent transition, our approach explicitly refines each state in situ, progressively steering it toward the optimal intermediate distribution. Across both text and image domains, we evaluate IterRef on diverse discrete diffusion models and observe consistent improvements in reward-guided generation quality. In particular, IterRef achieves striking gains under low compute budgets, far surpassing prior state-of-the-art baselines.

cs.LG↗

arXiv2025

RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases

Recent advances have demonstrated the effectiveness of graph-based learning on relational databases (RDBs) for predictive tasks. Such approaches require transforming RDBs into graphs, a process we refer to as RDB-to-graph modeling, where rows of tables are represented as nodes and foreign-key relationships as edges. Yet, effective modeling of RDBs into graphs remains challenging. Specifically, there exist numerous ways to model RDBs into graphs, and performance on predictive tasks varies significantly depending on the chosen graph model of RDBs. In our analysis, we find that the best-performing graph model can yield up to a 10% higher performance compared to the common heuristic rule for graph modeling, which remains non-trivial to identify. To foster research on intelligent RDB-to-graph modeling, we introduce RDB2G-Bench, the first benchmark framework for evaluating such methods. We construct extensive datasets covering 5 real-world RDBs and 12 predictive tasks, resulting in around 50k graph model-performance pairs for efficient and reproducible evaluations. Thanks to our precomputed datasets, we were able to benchmark 10 automatic RDB-to-graph modeling methods on the 12 tasks about 380x faster than on-the-fly evaluation, which requires repeated GNN training. Our analysis of the datasets and benchmark results reveals key structural patterns affecting graph model effectiveness, along with practical implications for effective graph modeling. Our datasets and code are available at https://github.com/chlehdwon/RDB2G-Bench.

cs.LG↗

arXiv2025

Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding

The performance of a deep learning model on a specific task and dataset depends heavily on its neural architecture, motivating considerable efforts to rapidly and accurately identify architectures suited to the target task and dataset. To achieve this, researchers use machine learning models-typically neural architecture encoders-to predict the performance of a neural architecture. Many state-of-the-art encoders aim to capture information flow within a neural architecture, which reflects how information moves through the forward pass and backpropagation, via a specialized model structure. However, due to their complicated structures, these flow-based encoders are significantly slower to process neural architectures compared to simpler encoders, presenting a notable practical challenge. To address this, we propose FGP, a novel pre-training method for neural architecture encoding that trains an encoder to capture the information flow without requiring specialized model structures. FGP trains an encoder to reconstruct a flow surrogate, our proposed representation of the neural architecture's information flow. Our experiments show that FGP boosts encoder performance by up to 106% in Precision-1%, compared to the same encoder trained solely with supervised learning.

cs.LG↗

arXiv2025

Mobility-Aware Localization in mmWave Channel: Adaptive Hybrid Filtering Approach

Precise user localization and tracking enhances energy-efficient and ultra-reliable low latency applications in the next generation wireless networks. In addition to computational complexity and data association challenges with Kalman-filter localization techniques, estimation errors tend to grow as the user's trajectory speed increases. By exploiting mmWave signals for joint sensing and communication, our approach dispenses with additional sensors adopted in most techniques while retaining high resolution spatial cues. We present a hybrid mobility-aware adaptive framework that selects the Extended Kalman filter at pedestrian speed and the Unscented Kalman filter at vehicular speed. The scheme mitigates data-association problem and estimation errors through adaptive noise scaling, chi-square gating, Rauch-Tung-Striebel smoothing. Evaluations using Absolute Trajectory Error, Relative Pose Error, Normalized Estimated Error Squared and Root Mean Square Error metrics demonstrate roughly 30-60% improvement in their respective regimes indicating a clear advantage over existing approaches tailored to either indoor or static settings.

eess.SP↗

arXiv2025

Domain-Agnostic Scalable AI Safety Ensuring Framework

AI safety has emerged as a critical priority as these systems are increasingly deployed in real-world applications. We propose the first domain-agnostic AI safety ensuring framework that achieves strong safety guarantees while preserving high performance, grounded in rigorous theoretical foundations. Our framework includes: (1) an optimization component with chance constraints, (2) a safety classification model, (3) internal test data, (4) conservative testing procedures, (5) informative dataset quality measures, and (6) continuous approximate loss functions with gradient computation. Furthermore, to our knowledge, we mathematically establish the first scaling law in AI safety research, relating data quantity to safety-performance trade-offs. Experiments across reinforcement learning, natural language generation, and production planning validate our framework and demonstrate superior performance. Notably, in reinforcement learning, we achieve 3 collisions during 10M actions, compared with 1,000-3,000 for PPO-Lag baselines at equivalent performance levels -- a safety level unattainable by previous AI methods. We believe our framework opens a new foundation for safe AI deployment across safety-critical domains.

cs.AI↗

arXiv2025

'Hello, World!': Making GNNs Talk with LLMs

While graph neural networks (GNNs) have shown remarkable performance across diverse graph-related tasks, their high-dimensional hidden representations render them black boxes. In this work, we propose Graph Lingual Network (GLN), a GNN built on large language models (LLMs), with hidden representations in the form of human-readable text. Through careful prompt design, GLN incorporates not only the message passing module of GNNs but also advanced GNN techniques, including graph attention and initial residual connection. The comprehensibility of GLN's hidden representations enables an intuitive analysis of how node representations change (1) across layers and (2) under advanced GNN techniques, shedding light on the inner workings of GNNs. Furthermore, we demonstrate that GLN achieves strong zero-shot performance on node classification and link prediction, outperforming existing LLM-based baseline methods.

cs.LG↗

arXiv2025

A Self-Supervised Mixture-of-Experts Framework for Multi-behavior Recommendation

In e-commerce, where users face a vast array of possible item choices, recommender systems are vital for helping them discover suitable items they might otherwise overlook. While many recommender systems primarily rely on a user's purchase history, recent multi-behavior recommender systems incorporate various auxiliary user behaviors, such as item clicks and cart additions, to enhance recommendations. Despite their overall performance gains, their effectiveness varies considerably between visited items (i.e., those a user has interacted with through auxiliary behaviors) and unvisited items (i.e., those with which the user has had no such interactions). Specifically, our analysis reveals that (1) existing multi-behavior recommender systems exhibit a significant gap in recommendation quality between the two item types (visited and unvisited items) and (2) achieving strong performance on both types with a single model architecture remains challenging. To tackle these issues, we propose a novel multi-behavior recommender system, MEMBER. It employs a mixture-of-experts framework, with experts designed to recommend the two item types, respectively. Each expert is trained using a self-supervised method specialized for its design goal. In our comprehensive experiments, we show the effectiveness of MEMBER across both item types, achieving up to 65.46% performance gain over the best competitor in terms of Hit Ratio@20.

cs.IR↗

arXiv2025

Deep Learning and Matrix Completion-aided IoT Network Localization in the Outlier Scenarios

In this paper, we propose a deep learning and matrix completion aided approach for recovering an outlier contaminated Euclidean distance matrix D in IoT network localization. Unlike conventional localization techniques that search the solution over a whole set of matrices, the proposed technique restricts the search to the set of Euclidean distance matrices. Specifically, we express D as a function of the sensor coordinate matrix X that inherently satisfies the unique properties of D, and then jointly recover D and X using a deep neural network. To handle outliers effectively, we model them as a sparse matrix L and add a regularization term of L into the optimization problem. We then solve the problem by alternately updating X, D, and L. Numerical experiments demonstrate that the proposed technique can recover the location information of sensors accurately even in the presence of outliers.

cs.LG↗

arXiv2025

Test-time Alignment of Diffusion Models without Reward Over-optimization

Diffusion models excel in generative tasks, but aligning them with specific objectives while maintaining their versatility remains challenging. Existing fine-tuning methods often suffer from reward over-optimization, while approximate guidance approaches fail to optimize target rewards effectively. Addressing these limitations, we propose a training-free, test-time method based on Sequential Monte Carlo (SMC) to sample from the reward-aligned target distribution. Our approach, tailored for diffusion sampling and incorporating tempering techniques, achieves comparable or superior target rewards to fine-tuning methods while preserving diversity and cross-reward generalization. We demonstrate its effectiveness in single-reward optimization, multi-objective scenarios, and online black-box optimization. This work offers a robust solution for aligning diffusion models with diverse downstream objectives without compromising their general capabilities. Code is available at https://github.com/krafton-ai/DAS.

cs.LG↗