Juyong Lee

Seunghyuk Cho, Juyong Lee, Jaesik Park et al.

We present a rotated hyperbolic wrapped normal distribution (RoWN), a simple yet effective alteration of a hyperbolic wrapped normal distribution (HWN). The HWN expands the domain of probabilistic modeling from Euclidean to hyperbolic space, where a tree can be embedded with arbitrary low distortion in theory. In this work, we analyze the geometric properties of the diagonal HWN, a standard choice of distribution in probabilistic modeling. The analysis shows that the distribution is inappropriate to represent the data points at the same hierarchy level through their angular distance with the same norm in the Poincaré disk model. We then empirically verify the presence of limitations of HWN, and show how RoWN, the proposed distribution, can alleviate the limitations on various hierarchical datasets, including noisy synthetic binary tree, WordNet, and Atari 2600 Breakout. The code is available at https://github.com/ml-postech/RoWN.

Juyong Lee, Seokjun Ahn, Jaesik Park

We present a novel method of learning style-agnostic representation using both style transfer and adversarial learning in the reinforcement learning framework. The style, here, refers to task-irrelevant details such as the color of the background in the images, where generalizing the learned policy across environments with different styles is still a challenge. Focusing on learning style-agnostic representations, our method trains the actor with diverse image styles generated from an inherent adversarial style perturbation generator, which plays a min-max game between the actor and the generator, without demanding expert knowledge for data augmentation or additional class labels for adversarial training. We verify that our method achieves competitive or better performances than the state-of-the-art approaches on Procgen and Distracting Control Suite benchmarks, and further investigate the features extracted from our model, showing that the model better captures the invariants and is less distracted by the shifted style. The code is available at https://github.com/POSTECH-CVLab/style-agnostic-RL.

Seunghyuk Cho, Juyong Lee, Dongwoo Kim

We propose a Gaussian manifold variational auto-encoder (GM-VAE) whose latent space consists of a set of Gaussian distributions. It is known that the set of the univariate Gaussian distributions with the Fisher information metric form a hyperbolic space, which we call a Gaussian manifold. To learn the VAE endowed with the Gaussian manifolds, we propose a pseudo-Gaussian manifold normal distribution based on the Kullback-Leibler divergence, a local approximation of the squared Fisher-Rao distance, to define a density over the latent space. In experiments, we demonstrate the efficacy of GM-VAE on two different tasks: density estimation of image datasets and environment modeling in model-based reinforcement learning. GM-VAE outperforms the other variants of hyperbolic- and Euclidean-VAEs on density estimation tasks and shows competitive performance in model-based reinforcement learning. We observe that our model provides strong numerical stability, addressing a common limitation reported in previous hyperbolic-VAEs.

Tien-Cuong Bui, Injae Chung, Wonjun Lee et al.

Predicting immunoglobulin-antigen (Ig-Ag) binding remains a significant challenge due to the paucity of experimentally-resolved complexes and the limited accuracy of de novo Ig structure prediction. We introduce IgPose, a generalizable framework for Ig-Ag pose identification and scoring, built on a generative data-augmentation pipeline. To mitigate data scarcity, we constructed the Structural Immunoglobulin Decoy Database (SIDD), a comprehensive repository of high-fidelity synthetic decoys. IgPose integrates equivariant graph neural networks, ESM-2 embeddings, and gated recurrent units to synergistically capture both geometric and evolutionary features. We implemented interface-focused k-hop sampling with biologically guided pooling to enhance generalization across diverse interfaces. The framework comprises two sub-networks--IgPoseClassifier for binding pose discrimination and IgPoseScore for DockQ score estimation--and achieves robust performance on curated internal test sets and the CASP-16 benchmark compared to physics and deep learning baselines. IgPose serves as a versatile computational tool for high-throughput antibody discovery pipelines by providing accurate pose filtering and ranking. IgPose is available on GitHub (https://github.com/arontier/igpose).

Juyong Lee, Dongyoon Hahm, June Suk Choi et al.

Autonomous agents powered by large language models (LLMs) show promising potential in assistive tasks across various domains, including mobile device control. As these agents interact directly with personal information and device settings, ensuring their safe and reliable behavior is crucial to prevent undesirable outcomes. However, no benchmark exists for standardized evaluation of the safety of mobile device-control agents. In this work, we introduce MobileSafetyBench, a benchmark designed to evaluate the safety of device-control agents within a realistic mobile environment based on Android emulators. We develop a diverse set of tasks involving interactions with various mobile applications, including messaging and banking applications, challenging agents with managing risks encompassing misuse and negative side effects. These tasks include tests to evaluate the safety of agents in daily scenarios as well as their robustness against indirect prompt injection attacks. Our experiments demonstrate that baseline agents, based on state-of-the-art LLMs, often fail to effectively prevent harm while performing the tasks. To mitigate these safety concerns, we propose a prompting method that encourages agents to prioritize safety considerations. While this method shows promise in promoting safer behaviors, there is still considerable room for improvement to fully earn user trust. This highlights the urgent need for continued research to develop more robust safety mechanisms in mobile environments. We open-source our benchmark at: https://mobilesafetybench.github.io/.

Dongjun Lee, Juyong Lee, Kyuyoung Kim et al.

Recent advances in large language models (LLMs) have led to a growing interest in developing LLM-based agents for automating web tasks. However, these agents often struggle with even simple tasks on real-world websites due to their limited capability to understand and process complex web page structures. In this work, we introduce LCoW, a framework for Learning language models to Contextualize complex Web pages into a more comprehensible form, thereby enhancing decision making by LLM agents. LCoW decouples web page understanding from decision making by training a separate contextualization module to transform complex web pages into comprehensible format, which are then utilized by the decision-making agent. We demonstrate that our contextualization module effectively integrates with LLM agents of various scales to significantly enhance their decision-making capabilities in web automation tasks. Notably, LCoW improves the success rates of closed-source LLMs (e.g., Gemini-1.5-flash, GPT-4o, Claude-3.5-Sonnet) by an average of 15.6%, and demonstrates a 23.7% average improvement in success rates for open-source LMs (e.g., Llama-3.1-8B, Llama-3.1-70B) on the WorkArena benchmark. Moreover, the Gemini-1.5-flash agent with LCoW achieves state-of-the-art results on the WebShop benchmark, outperforming human experts. The relevant code materials are available at our project page: https://lcowiclr2025.github.io.

Juyong Lee, Seunghyuk Cho

Consistency training, which exploits both supervised and unsupervised learning with different augmentations on image, is an effective method of utilizing unlabeled data in semi-supervised learning (SSL) manner. Here, we present another version of the method with Grad-CAM consistency loss, so it can be utilized in training model with better generalization and adjustability. We show that our method improved the baseline ResNet model with at most 1.44 % and 0.31 $\pm$ 0.59 %p accuracy improvement on average with CIFAR-10 dataset. We conducted ablation study comparing to using only psuedo-label for consistency training. Also, we argue that our method can adjust in different environments when targeted to different units in the model. The code is available: https://github.com/gimme1dollar/gradcam-consistency-semi-sup.

Juyong Lee, Taywon Min, Minyong An et al.

Mobile device control agents can largely enhance user interactions and productivity by automating daily tasks. However, despite growing interest in developing practical agents, the absence of a commonly adopted benchmark in this area makes it challenging to quantify scientific progress. In this work, we introduce B-MoCA: a novel benchmark with interactive environments for evaluating and developing mobile device control agents. To create a realistic benchmark, we develop B-MoCA based on the Android operating system and define 131 common daily tasks. Importantly, we incorporate a randomization feature that changes the configurations of mobile devices, including user interface layouts and language settings, to assess generalization performance. We benchmark diverse agents, including agents employing large language models (LLMs) or multi-modal LLMs as well as agents trained with imitation learning using human expert demonstrations. While these agents demonstrate proficiency in executing straightforward tasks, their poor performance on complex tasks highlights significant opportunities for future research to improve effectiveness. Our source code is publicly available at https://b-moca.github.io.

Taewook Nam, Juyong Lee, Jesse Zhang et al.

We propose a framework that leverages foundation models as teachers, guiding a reinforcement learning agent to acquire semantically meaningful behavior without human feedback. In our framework, the agent receives task instructions grounded in a training environment from large language models. Then, a vision-language model guides the agent in learning the multi-task language-conditioned policy by providing reward feedback. We demonstrate that our method can learn semantically meaningful skills in a challenging open-ended MineDojo environment while prior unsupervised skill discovery methods struggle. Additionally, we discuss observed challenges of using off-the-shelf foundation models as teachers and our efforts to address them.

Sayash Kapoor, Benedikt Stroebl, Peter Kirgis et al. · microsoft-research, princeton

AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of how well agents really work. We introduce the Holistic Agent Leaderboard (HAL) to address these challenges. We make three main contributions. First, we provide a standardized evaluation harness that orchestrates parallel evaluations across hundreds of VMs, reducing evaluation time from weeks to hours while eliminating common implementation bugs. Second, we conduct three-dimensional analysis spanning models, scaffolds, and benchmarks. We validate the harness by conducting 21,730 agent rollouts across 9 models and 9 benchmarks in coding, web navigation, science, and customer service with a total cost of about $40,000. Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs. Third, we use LLM-aided log inspection to uncover previously unreported behaviors, such as searching for the benchmark on HuggingFace instead of solving a task, or misusing credit cards in flight booking tasks. We share all agent logs, comprising 2.5B tokens of language model calls, to incentivize further research into agent behavior. By standardizing how the field evaluates agents and addressing common pitfalls in agent evaluation, we hope to shift the focus from agents that ace benchmarks to agents that work reliably in the real world.

Yongjin Yang, Sinjae Kang, Juyong Lee et al.

Training large language model (LLM) agents to acquire necessary skills and perform diverse tasks within an environment is gaining interest as a means to enable open-endedness. However, creating the training dataset for their skill acquisition faces several challenges. Manual trajectory collection requires significant human effort. Another approach, where LLMs directly propose tasks to learn, is often invalid, as the LLMs lack knowledge of which tasks are actually feasible. Moreover, the generated data may not provide a meaningful learning signal, as agents often already perform well on the proposed tasks. To address this, we propose a novel automatic skill discovery framework EXIF for LLM-powered agents, designed to improve the feasibility of generated target behaviors while accounting for the agents' capabilities. Our method adopts an exploration-first strategy by employing an exploration agent (Alice) to train the target agent (Bob) to learn essential skills in the environment. Specifically, Alice first interacts with the environment to retrospectively generate a feasible, environment-grounded skill dataset, which is then used to train Bob. Crucially, we incorporate an iterative feedback loop, where Alice evaluates Bob's performance to identify areas for improvement. This feedback then guides Alice's next round of exploration, forming a closed-loop data generation process. Experiments on Webshop and Crafter demonstrate EXIF's ability to effectively discover meaningful skills and iteratively expand the capabilities of the trained agent without any human intervention, achieving substantial performance improvements. Interestingly, we observe that setting Alice to the same model as Bob also notably improves performance, demonstrating EXIF's potential for building a self-evolving system.

Juheon Choi, Juyong Lee, Jian Kim et al.

When working on digital devices, people often face distractions that can lead to a decline in productivity and efficiency, as well as negative psychological and emotional impacts. To address this challenge, we introduce a novel Artificial Intelligence (AI) assistant that elicits a user's intention, assesses whether ongoing activities are in line with that intention, and provides gentle nudges when deviations occur. The system leverages a large language model to analyze screenshots, application titles, and URLs, issuing notifications when behavior diverges from the stated goal. Its detection accuracy is refined through initial clarification dialogues and continuous user feedback. In a three-week, within-subjects field deployment with 22 participants, we compared our assistant to both a rule-based intent reminder system and a passive baseline that only logged activity. Results indicate that our AI assistant effectively supports users in maintaining focus and aligning their digital behavior with their intentions. Our source code is publicly available at https://intentassistant.github.io

Jungmin Lee, Seonghyuk Hong, Juyong Lee et al.

We introduce InsideOut, an extension of 3D Gaussian splatting (3DGS) that bridges the gap between high-fidelity RGB surface details and subsurface X-ray structures. The fusion of RGB and X-ray imaging is invaluable in fields such as medical diagnostics, cultural heritage restoration, and manufacturing. We collect new paired RGB and X-ray data, perform hierarchical fitting to align RGB and X-ray radiative Gaussian splats, and propose an X-ray reference loss to ensure consistent internal structures. InsideOut effectively addresses the challenges posed by disparate data representations between the two modalities and limited paired datasets. This approach significantly extends the applicability of 3DGS, enhancing visualization, simulation, and non-destructive testing capabilities across various domains.

Juyong Lee, Youngsang Cho

As the volatility of electricity demand increases owing to climate change and electrification, the importance of accurate peak load forecasting is increasing. Traditional peak load forecasting has been conducted through time series-based models; however, recently, new models based on machine or deep learning are being introduced. This study performs a comparative analysis to determine the most accurate peak load-forecasting model for Korea, by comparing the performance of time series, machine learning, and hybrid models. Seasonal autoregressive integrated moving average with exogenous variables (SARIMAX) is used for the time series model. Artificial neural network (ANN), support vector regression (SVR), and long short-term memory (LSTM) are used for the machine learning models. SARIMAX-ANN, SARIMAX-SVR, and SARIMAX-LSTM are used for the hybrid models. The results indicate that the hybrid models exhibit significant improvement over the SARIMAX model. The LSTM-based models outperformed the others; the single and hybrid LSTM models did not exhibit a significant performance difference. In the case of Korea's highest peak load in 2019, the predictive power of the LSTM model proved to be greater than that of the SARIMAX-LSTM model. The LSTM, SARIMAX-SVR, and SARIMAX-LSTM models outperformed the current time series-based forecasting model used in Korea. Thus, Korea's peak load-forecasting performance can be improved by including machine learning or hybrid models.

Seunghyuk Cho, Minsoo Koo, Dongwoo Kim et al.

With rise of interventional cardiology, Catheter Ablation Therapy (CAT) has established itself as a first-line solution to treat cardiac arrhythmia. Although CAT is a promising technique, cardiologist lacks vision inside the body during the procedure, which may cause serious clinical syndromes. To support accurate clinical procedure, Contact Force Sensing (CFS) system is developed to find a position of the catheter tip through the measure of contact force between catheter and heart tissue. However, the practical usability of commercialized CFS systems is not fully understood due to inaccuracy in the measurement. To support the development of more accurate system, we develop a full pipeline of CFS system with newly collected benchmark dataset through a contact force sensing catheter in simplest hardware form. Our dataset was roughly collected with human noise to increase data diversity. Through the analysis of the dataset, we identify a problem defined as Shift of Reference (SoR), which prevents accurate measurement of contact force. To overcome the problem, we conduct the contact force estimation via standard deep neural networks including for Recurrent Neural Network (RNN), Fully Convolutional Network (FCN) and Transformer. An average error in measurement for RNN, FCN and Transformer are, respectively, 2.46g, 3.03g and 3.01g. Through these studies, we try to lay a groundwork, serve a performance criteria for future CFS system research and open a publicly available dataset to public.