arXiv subjects

Sunghwan Kim

Publications and source records attributed to Sunghwan Kim.

At least 37 records · Page 2Linked to original sources

arXiv2025

Cavity-Mediated Coupling between Local and Nonlocal Modes in Landau Polaritons

The multimode ultrastrong coupling (USC) regime has emerged as a novel platform for accessing previously inaccessible phenomena in cavity quantum electrodynamics. Of particular interest are cavity-mediated correlations between local and nonlocal excitations, or equivalently, between modes at zero and finite in-plane momentum modes, which offer new opportunities for controlling light-matter interactions across space. However, direct experimental evidence of such interactions has remained elusive. Here, we demonstrate nonlocal multimode coupling in a Landau polariton system, where cavity photons simultaneously interact with the zero-momentum cyclotron resonance and finite-momentum magnetoplasmons of a two-dimensional electron gas in a GaAs quantum well. Our slot cavities, with their subwavelength mode volumes, supply in-plane momentum components that enable the excitation of finite-momentum matter modes. Terahertz time-domain magnetospectroscopy measurements reveal a clear splitting of the upper-polariton branch, arising from hybridization between magnetoplasmon modes and the cavity--cyclotron-resonance hybrids. Extracted coupling strengths confirm USC of the cyclotron resonance and strong coupling of the magnetoplasmon modes to the cavity field, respectively. The experimental results are well captured by the multimode Hopfield model and finite-element simulations. These findings establish a pathway for engineering multimode light-matter interactions involving zero- and finite-momentum matter modes in the USC regime.

quant-ph↗

arXiv2025

Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Action

Conversational Recommender Systems (CRSs)aim to engage users in dialogue to provide tailored recommendations. While traditional CRSs focus on eliciting preferences and retrieving items, real-world e-commerce interactions involve more complex decision-making, where users consider multiple factors beyond simple attributes. To capture this complexity, we introduce Conversational Sales (CSALES), a novel task that integrates preference elicitation, recommendation, and persuasion within a unified conversational framework. To support realistic and systematic evaluation, we present CSUSER, an evaluation protocol with LLM-based user simulator grounded in real-world behavioral data by modeling fine-grained user profiles for personalized interaction. We also propose CSI, a conversational sales agent that proactively infers contextual user profiles and strategically selects actions through conversation. Comprehensive experiments show that CSI significantly improves both recommendation success and persuasive effectiveness across diverse user profiles.

cs.IR↗

arXiv2025

MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting, appending all past turns regardless of their relevance. This leads to unbounded memory growth, increased computational costs, and degraded reasoning performance on out-of-distribution input lengths. We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks. At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning. This state integrates prior memory with new observations from the environment while strategically discarding irrelevant or redundant information. To support training in more realistic and compositional settings, we propose a simple yet effective and scalable approach to constructing multi-turn environments by composing existing datasets into arbitrarily complex task sequences. Experiments across three domains, including internal retrieval QA, open-domain web QA, and multi-turn web shopping, show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task, and generalizes beyond the training horizon. Our results demonstrate the promise of reasoning-driven memory consolidation as a scalable alternative to existing solutions for training long-horizon interactive agents, where both efficiency and performance are optimized.

cs.CL↗

arXiv2025

LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study

The remarkable reasoning and generalization capabilities of Large Language Models (LLMs) have paved the way for their expanding applications in embodied AI, robotics, and other real-world tasks. To effectively support these applications, grounding in spatial and temporal understanding in multimodal environments is essential. To this end, recent works have leveraged scene graphs, a structured representation that encodes entities, attributes, and their relationships in a scene. However, a comprehensive evaluation of LLMs' ability to utilize scene graphs remains limited. In this work, we introduce Text-Scene Graph (TSG) Bench, a benchmark designed to systematically assess LLMs' ability to (1) understand scene graphs and (2) generate them from textual narratives. With TSG Bench we evaluate 11 LLMs and reveal that, while models perform well on scene graph understanding, they struggle with scene graph generation, particularly for complex narratives. Our analysis indicates that these models fail to effectively decompose discrete scenes from a complex narrative, leading to a bottleneck when generating scene graphs. These findings underscore the need for improved methodologies in scene graph generation and provide valuable insights for future research. The demonstration of our benchmark is available at https://tsg-bench.netlify.app. Additionally, our code and evaluation data are publicly available at https://github.com/docworlds/tsg-bench.

cs.CL↗

arXiv2025

Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation

Emotional Support Conversation (ESC) is a task aimed at alleviating individuals' emotional distress through daily conversation. Given its inherent complexity and non-intuitive nature, ESConv dataset incorporates support strategies to facilitate the generation of appropriate responses. Recently, despite the remarkable conversational ability of large language models (LLMs), previous studies have suggested that they often struggle with providing useful emotional support. Hence, this work initially analyzes the results of LLMs on ESConv, revealing challenges in selecting the correct strategy and a notable preference for a specific strategy. Motivated by these, we explore the impact of the inherent preference in LLMs on providing emotional support, and consequently, we observe that exhibiting high preference for specific strategies hinders effective emotional support, aggravating its robustness in predicting the appropriate strategy. Moreover, we conduct a methodological study to offer insights into the necessary approaches for LLMs to serve as proficient emotional supporters. Our findings emphasize that (1) low preference for specific strategies hinders the progress of emotional support, (2) external assistance helps reduce preference bias, and (3) existing LLMs alone cannot become good emotional supporters. These insights suggest promising avenues for future research to enhance the emotional intelligence of LLMs.

cs.CL↗

arXiv2025

Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization

Reward models (RMs) play a crucial role in reinforcement learning from human feedback (RLHF), aligning model behavior with human preferences. However, existing benchmarks for reward models show a weak correlation with the performance of optimized policies, suggesting that they fail to accurately assess the true capabilities of RMs. To bridge this gap, we explore several evaluation designs through the lens of reward overoptimization\textemdash a phenomenon that captures both how well the reward model aligns with human preferences and the dynamics of the learning signal it provides to the policy. The results highlight three key findings on how to construct a reliable benchmark: (i) it is important to minimize differences between chosen and rejected responses beyond correctness, (ii) evaluating reward models requires multiple comparisons across a wide range of chosen and rejected responses, and (iii) given that reward models encounter responses with diverse representations, responses should be sourced from a variety of models. However, we also observe that a extremely high correlation with degree of overoptimization leads to comparatively lower correlation with certain downstream performance. Thus, when designing a benchmark, it is desirable to use the degree of overoptimization as a useful tool, rather than the end goal.

cs.LG↗

arXiv2025

MISO: Multiresolution Submap Optimization for Efficient Globally Consistent Neural Implicit Reconstruction

Neural implicit representations have had a significant impact on simultaneous localization and mapping (SLAM) by enabling robots to build continuous, differentiable, and high-fidelity 3D maps from sensor data. However, as the scale and complexity of the environment increase, neural SLAM approaches face renewed challenges in the back-end optimization process to keep up with runtime requirements and maintain global consistency. We introduce MISO, a hierarchical optimization approach that leverages multiresolution submaps to achieve efficient and scalable neural implicit reconstruction. For local SLAM within each submap, we develop a hierarchical optimization scheme with learned initialization that substantially reduces the time needed to optimize the implicit submap features. To correct estimation drift globally, we develop a hierarchical method to align and fuse the multiresolution submaps, leading to substantial acceleration by avoiding the need to decode the full scene geometry. MISO significantly improves computational efficiency and estimation accuracy of neural signed distance function (SDF) SLAM on large-scale real-world benchmarks.

cs.RO↗

arXiv2025

Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly buying a non-refundable flight ticket. By contrast, humans can avoid such an irreversible mistake, as we have an awareness of the potential outcomes (e.g., losing money) of our actions, also known as the "world model". Motivated by this, our study first starts with preliminary analyses, confirming the absence of world models in current LLMs (e.g., GPT-4o, Claude-3.5-Sonnet, etc.). Then, we present a World-model-augmented (WMA) web agent, which simulates the outcomes of its actions for better decision-making. To overcome the challenges in training LLMs as world models predicting next observations, such as repeated elements across observations and long HTML inputs, we propose a transition-focused observation abstraction, where the prediction objectives are free-form natural language descriptions exclusively highlighting important state differences between time steps. Experiments on WebArena and Mind2Web show that our world models improve agents' policy selection without training and demonstrate our agents' cost- and time-efficiency compared to recent tree-search-based agents.

cs.CL↗

arXiv2024

MediViSTA: Medical Video Segmentation via Temporal Fusion SAM Adaptation for Echocardiography

Despite achieving impressive results in general-purpose semantic segmentation with strong generalization on natural images, the Segment Anything Model (SAM) has shown less precision and stability in medical image segmentation. In particular, the original SAM architecture is designed for 2D natural images and is therefore not support to handle three-dimensional information, which is particularly important for medical imaging modalities that are often volumetric or video data. In this paper, we introduce MediViSTA, a parameter-efficient fine-tuning method designed to adapt the vision foundation model for medical video, with a specific focus on echocardiographic segmentation. To achieve spatial adaptation, we propose a frequency feature fusion technique that injects spatial frequency information from a CNN branch. For temporal adaptation, we integrate temporal adapters within the transformer blocks of the image encoder. Using a fine-tuning strategy, only a small subset of pre-trained parameters is updated, allowing efficient adaptation to echocardiographic data. The effectiveness of our method has been comprehensively evaluated on three datasets, comprising two public datasets and one multi-center in-house dataset. Our method consistently outperforms various state-of-the-art approaches without using any prompts. Furthermore, our model exhibits strong generalization capabilities on unseen datasets, surpassing the second-best approach by 2.15\% in Dice and 0.09 in temporal consistency. The results demonstrate the potential of MediViSTA to significantly advance echocardiographical video segmentation, offering improved accuracy and robustness in cardiac assessment applications.

eess.IV↗

arXiv2024

Applications of Generative AI (GAI) for Mobile and Wireless Networking: A Survey

The success of Artificial Intelligence (AI) in multiple disciplines and vertical domains in recent years has promoted the evolution of mobile networking and the future Internet toward an AI-integrated Internet-of-Things (IoT) era. Nevertheless, most AI techniques rely on data generated by physical devices (e.g., mobile devices and network nodes) or specific applications (e.g., fitness trackers and mobile gaming). Therefore, Generative AI (GAI), a.k.a. AI-generated content (AIGC), has emerged as a powerful AI paradigm; thanks to its ability to efficiently learn complex data distributions and generate synthetic data to represent the original data in various forms. This impressive feature is projected to transform the management of mobile networking and diversify the current services and applications provided. On this basis, this work presents a concise tutorial on the role of GAIs in mobile and wireless networking. In particular, this survey first provides the fundamentals of GAI and representative GAI models, serving as an essential preliminary to the understanding of GAI's applications in mobile and wireless networking. Then, this work provides a comprehensive review of state-of-the-art studies and GAI applications in network management, wireless security, semantic communication, and lessons learned from the open literature. Finally, this work summarizes the current research on GAI for mobile and wireless networking by outlining important challenges that need to be resolved to facilitate the development and applicability of GAI in this edge-cutting area.

cs.NI↗

arXiv2024

Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory

Recently, the demand for psychological counseling has significantly increased as more individuals express concerns about their mental health. This surge has accelerated efforts to improve the accessibility of counseling by using large language models (LLMs) as counselors. To ensure client privacy, training open-source LLMs faces a key challenge: the absence of realistic counseling datasets. To address this, we introduce Cactus, a multi-turn dialogue dataset that emulates real-life interactions using the goal-oriented and structured approach of Cognitive Behavioral Therapy (CBT). We create a diverse and realistic dataset by designing clients with varied, specific personas, and having counselors systematically apply CBT techniques in their interactions. To assess the quality of our data, we benchmark against established psychological criteria used to evaluate real counseling sessions, ensuring alignment with expert evaluations. Experimental results demonstrate that Camel, a model trained with Cactus, outperforms other models in counseling skills, highlighting its effectiveness and potential as a counseling agent. We make our data, model, and code publicly available.

cs.CL↗

arXiv2024

Evaluating Robustness of Reward Models for Mathematical Reasoning

Reward models are key in reinforcement learning from human feedback (RLHF) systems, aligning the model behavior with human preferences. Particularly in the math domain, there have been plenty of studies using reward models to align policies for improving reasoning capabilities. Recently, as the importance of reward models has been emphasized, RewardBench is proposed to understand their behavior. However, we figure out that the math subset of RewardBench has different representations between chosen and rejected completions, and relies on a single comparison, which may lead to unreliable results as it only see an isolated case. Therefore, it fails to accurately present the robustness of reward models, leading to a misunderstanding of its performance and potentially resulting in reward hacking. In this work, we introduce a new design for reliable evaluation of reward models, and to validate this, we construct RewardMATH, a benchmark that effectively represents the robustness of reward models in mathematical reasoning tasks. We demonstrate that the scores on RewardMATH strongly correlate with the results of optimized policy and effectively estimate reward overoptimization, whereas the existing benchmark shows almost no correlation. The results underscore the potential of our design to enhance the reliability of evaluation, and represent the robustness of reward model. We make our code and data publicly available.

cs.LG↗

arXiv2024

Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning

Offline multi-agent reinforcement learning (MARL) is increasingly recognized as crucial for effectively deploying RL algorithms in environments where real-time interaction is impractical, risky, or costly. In the offline setting, learning from a static dataset of past interactions allows for the development of robust and safe policies without the need for live data collection, which can be fraught with challenges. Building on this foundational importance, we present EAQ, Episodes Augmentation guided by Q-total loss, a novel approach for offline MARL framework utilizing diffusion models. EAQ integrates the Q-total function directly into the diffusion model as a guidance to maximize the global returns in an episode, eliminating the need for separate training. Our focus primarily lies on cooperative scenarios, where agents are required to act collectively towards achieving a shared goal-essentially, maximizing global returns. Consequently, we demonstrate that our episodes augmentation in a collaborative manner significantly boosts offline MARL algorithm compared to the original dataset, improving the normalized return by +17.3% and +12.9% for medium and poor behavioral policies in SMAC simulator, respectively.

cs.LG↗

arXiv2024

Textual Query-Driven Mask Transformer for Domain Generalized Segmentation

In this paper, we introduce a method to tackle Domain Generalized Semantic Segmentation (DGSS) by utilizing domain-invariant semantic knowledge from text embeddings of vision-language models. We employ the text embeddings as object queries within a transformer-based segmentation framework (textual object queries). These queries are regarded as a domain-invariant basis for pixel grouping in DGSS. To leverage the power of textual object queries, we introduce a novel framework named the textual query-driven mask transformer (tqdm). Our tqdm aims to (1) generate textual object queries that maximally encode domain-invariant semantics and (2) enhance the semantic clarity of dense visual features. Additionally, we suggest three regularization losses to improve the efficacy of tqdm by aligning between visual and textual features. By utilizing our method, the model can comprehend inherent semantic information for classes of interest, enabling it to generalize to extreme domains (e.g., sketch style). Our tqdm achieves 68.9 mIoU on GTA5$\rightarrow$Cityscapes, outperforming the prior state-of-the-art method by 2.5 mIoU. The project page is available at https://byeonghyunpak.github.io/tqdm.

cs.CV↗

arXiv2024

A Novel Paradigm Shift for Next-Generation: Symbiotic Backscatter Rate-Splitting Multiple Access Systems

Next-generation wireless networks are projected to empower a broad range of Internet-of-things (IoT) applications and services with extreme data rates, posing new challenges in delivering large-scale connectivity at a low cost to current communication paradigms. Rate-splitting multiple access (RSMA) is one of the most spotlight nominees, conceived to address spectrum scarcity while reaching massive connectivity. Meanwhile, symbiotic communication is said to be an inexpensive way to realize future IoT on a large scale. To reach the goal of spectrum efficiency improvement and low energy consumption, we merge these advances by means of introducing a novel paradigm shift, called symbiotic backscatter RSMA, for the next generation. Specifically, we first establish the way to operate the symbiotic system to assist the readers in apprehending the proposed paradigm, then guide detailed design in beamforming weights with four potential gain-control (GC) strategies for enhancing symbiotic communication, and finally provide an information-theoretic framework using a new metric, called symbiotic outage probability (SOP) to characterize the proposed system performance. Through numerical result experiments, we show that the developed framework can accurately predict the actual SOP and the efficacy of the proposed GC strategies in improving the SOP performance.

cs.IT↗

arXiv2023

How to Mask in Error Correction Code Transformer: Systematic and Double Masking

In communication and storage systems, error correction codes (ECCs) are pivotal in ensuring data reliability. As deep learning's applicability has broadened across diverse domains, there is a growing research focus on neural network-based decoders that outperform traditional decoding algorithms. Among these neural decoders, Error Correction Code Transformer (ECCT) has achieved the state-of-the-art performance, outperforming other methods by large margins. To further enhance the performance of ECCT, we propose two novel methods. First, leveraging the systematic encoding technique of ECCs, we introduce a new masking matrix for ECCT, aiming to improve the performance and reduce the computational complexity. Second, we propose a novel transformer architecture of ECCT called a double-masked ECCT. This architecture employs two different mask matrices in a parallel manner to learn more diverse features of the relationship between codeword bits in the masked self-attention blocks. Extensive simulation results show that the proposed double-masked ECCT outperforms the conventional ECCT, achieving the state-of-the-art decoding performance with significant margins.

cs.LG↗

arXiv2023

Texture Learning Domain Randomization for Domain Generalized Segmentation

Deep Neural Networks (DNNs)-based semantic segmentation models trained on a source domain often struggle to generalize to unseen target domains, i.e., a domain gap problem. Texture often contributes to the domain gap, making DNNs vulnerable to domain shift because they are prone to be texture-biased. Existing Domain Generalized Semantic Segmentation (DGSS) methods have alleviated the domain gap problem by guiding models to prioritize shape over texture. On the other hand, shape and texture are two prominent and complementary cues in semantic segmentation. This paper argues that leveraging texture is crucial for improving performance in DGSS. Specifically, we propose a novel framework, coined Texture Learning Domain Randomization (TLDR). TLDR includes two novel losses to effectively enhance texture learning in DGSS: (1) a texture regularization loss to prevent overfitting to source domain textures by using texture features from an ImageNet pre-trained model and (2) a texture generalization loss that utilizes random style images to learn diverse texture representations in a self-supervised manner. Extensive experimental results demonstrate the superiority of the proposed TLDR; e.g., TLDR achieves 46.5 mIoU on GTA-to-Cityscapes using ResNet-50, which improves the prior state-of-the-art method by 1.9 mIoU. The source code is available at https://github.com/ssssshwan/TLDR.

cs.CV↗

arXiv2019

Accelerated Training for CNN Distributed Deep Learning through Automatic Resource-Aware Layer Placement

The Convolutional Neural Network (CNN) model, often used for image classification, requires significant training time to obtain high accuracy. To this end, distributed training is performed with the parameter server (PS) architecture using multiple servers. Unfortunately, scalability has been found to be poor in existing architectures. We find that the PS network is the bottleneck as it communicates a large number of gradients and parameters with the many workers. This is because synchronization with the many workers has to occur at every step of training. Depending on the model, communication can be in the several hundred MBs per synchronization. In this paper, we propose a scheme to reduce network traffic through layer placement that considers the resources that each layer uses. Through analysis of the characteristics of CNN, we find that placement of layers can be done in an effective manner. We then incorporate this observation within the TensorFlow framework such that layers can be automatically placed for more efficient training. Our evaluation making use of this placement scheme show that training time can be significantly reduced without loss of accuracy for many CNN models.

cs.DC↗