arXiv subjects

Sangeun Oh

Publications and source records attributed to Sangeun Oh.

6 recordsLinked to original sources

arXiv2026

Attractive statistical forces and Pauli crystal formation in trapped Fermi gases

Exchange statistics endows identical particles with an effective "statistical potential", whose familiar exact form is two-body and purely repulsive for fermions. Here we construct an exact collective many-body form: the thermodynamics of $N$ trapped ideal fermions maps onto classical distinguishable particles governed by a single potential -- exactly for harmonic confinement at all temperatures, and to leading semiclassical order for arbitrary potentials. The associated force separates canonically into pairwise contributions, which for $N\geq 3$ can turn attractive, governed by a simple geometric criterion. Classical minimization reproduces observed few-body Pauli-crystal symmetries and agrees with the $N=55$ ground-state probability maximum at sub-percent shell accuracy. Heating drives discrete structural transitions accompanied by a crossover of the strongest force from attractive to repulsive. Both the potential and its forces are directly computable from existing single-shot imaging data, turning quantum exchange into measurable classical mechanics.

cond-mat.stat-mech↗

arXiv2026

MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents

Mobile GUI Agents, AI agents capable of interacting with mobile applications on behalf of users, have the potential to transform human computer interaction. However, current evaluation practices for GUI agents face two fundamental limitations. First, they either rely on single path offline benchmarks or online live benchmarks. Offline benchmarks using static, single path annotated datasets unfairly penalize valid alternative actions, while online benchmarks suffer from poor scalability and reproducibility due to the dynamic and unpredictable nature of live evaluation. Second, existing benchmarks treat agents as monolithic black boxes, overlooking the contributions of individual components, which often leads to unfair comparisons or obscures key performance bottlenecks. To address these limitations, we present MobiBench, the first modular and multi path aware offline benchmarking framework for mobile GUI agents that enables high fidelity, scalable, and reproducible evaluation entirely in offline settings. Our experiments demonstrate that MobiBench achieves 94.72 percent agreement with human evaluators, on par with carefully engineered online benchmarks, while preserving the scalability and reproducibility of static offline benchmarks. Furthermore, our comprehensive module level analysis uncovers several key insights, including a systematic evaluation of diverse techniques used in mobile GUI agents, optimal module configurations across model scales, the inherent limitations of current LFMs, and actionable guidelines for designing more capable and cost efficient mobile agents.

cs.AI↗

arXiv2026

Leveraging LLMs for Efficient and Personalized Smart Home Automation

The proliferation of smart home devices has increased the complexity of controlling and managing them, leading to user fatigue. In this context, large language models (LLMs) offer a promising solution by enabling natural-language interfaces for Internet of Things (IoT) control. However, existing LLM-based approaches suffer from unreliable and inefficient device control due to the non-deterministic nature of LLMs, high inference latency and cost, and limited personalization. To address these challenges, we present IoTGPT, an LLM-based smart home agent designed to execute IoT commands in a reliable, efficient, and personalized manner. Inspired by how humans manage complex tasks, IoTGPT decomposes user instructions into subtasks and memorizes them. By reusing learned subtasks, subsequent instructions can be processed more efficiently with fewer LLM calls, improving reliability and reducing both latency and cost. IoTGPT also supports fine-grained personalization by adapting individual subtasks to user preferences. Our evaluation demonstrates that IoTGPT outperforms baselines in accuracy, latency/cost, and personalization, while reducing user workload.

cs.HC↗

arXiv2025

VeriSafe Agent: Safeguarding Mobile GUI Agent via Logic-based Action Verification

Large Foundation Models (LFMs) have unlocked new possibilities in human-computer interaction, particularly with the rise of mobile Graphical User Interface (GUI) Agents capable of interacting with mobile GUIs. These agents allow users to automate complex mobile tasks through simple natural language instructions. However, the inherent probabilistic nature of LFMs, coupled with the ambiguity and context-dependence of mobile tasks, makes LFM-based automation unreliable and prone to errors. To address this critical challenge, we introduce VeriSafe Agent (VSA): a formal verification system that serves as a logically grounded safeguard for Mobile GUI Agents. VSA deterministically ensures that an agent's actions strictly align with user intent before executing the action. At its core, VSA introduces a novel autoformalization technique that translates natural language user instructions into a formally verifiable specification. This enables runtime, rule-based verification of agent's actions, detecting erroneous actions even before they take effect. To the best of our knowledge, VSA is the first attempt to bring the rigor of formal verification to GUI agents, bridging the gap between LFM-driven actions and formal software verification. We implement VSA using off-the-shelf LFM services (GPT-4o) and evaluate its performance on 300 user instructions across 18 widely used mobile apps. The results demonstrate that VSA achieves 94.33%-98.33% accuracy in verifying agent actions, outperforming existing LFM-based verification methods by 30.00%-16.33%, and increases the GUI agent's task completion rate by 90%-130%.

cs.HC↗

arXiv2024

Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation

The advent of large language models (LLMs) has opened up new opportunities in the field of mobile task automation. Their superior language understanding and reasoning capabilities allow users to automate complex and repetitive tasks. However, due to the inherent unreliability and high operational cost of LLMs, their practical applicability is quite limited. To address these issues, this paper introduces MobileGPT, an innovative LLM-based mobile task automator equipped with a human-like app memory. MobileGPT emulates the cognitive process of humans interacting with a mobile app -- explore, select, derive, and recall. This approach allows for a more precise and efficient learning of a task's procedure by breaking it down into smaller, modular sub-tasks that can be re-used, re-arranged, and adapted for various objectives. We implement MobileGPT using online LLMs services (GPT-3.5 and GPT-4) and evaluate its performance on a dataset of 185 tasks across 18 mobile apps. The results indicate that MobileGPT can automate and learn new tasks with 82.7% accuracy, and is able to adapt them to different contexts with near perfect (98.75%) accuracy while reducing both latency and cost by 62.5% and 68.8%, respectively, compared to the GPT-4 powered baseline.

cs.HC↗

arXiv2019

Deep Generative Design: Integration of Topology Optimization and Generative Models

Deep learning has recently been applied to various research areas of design optimization. This study presents the need and effectiveness of adopting deep learning for generative design (or design exploration) research area. This work proposes an artificial intelligent (AI)-based design automation framework that is capable of generating numerous design options which are not only aesthetic but also optimized for engineering performance. The proposed framework integrates topology optimization and deep generative models (e.g., generative adversarial networks (GANs)) in an iterative manner to explore new design options, thus generating a large number of designs starting from limited previous design data. In addition, anomaly detection can evaluate the novelty of generated designs, thus helping designers choose among design options. The 2D wheel design problem is applied as a case study for validation of the proposed framework. The framework manifests better aesthetics, diversity, and robustness of generated designs than previous generative design methods.

cs.LG↗