Author name cluster

Jihoon Kim

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

IROS Conference 2025 Conference Paper

Robust and Expressive Humanoid Motion Retargeting via Optimization-Based Rig Unification

Taemoon Jeong
Taehyun Byun
Jihoon Kim
Keunjun Choi
Jaesung Oh
Sungpyo Lee
Omar Darwish
Joohyung Kim

Humanoid robots are increasingly being developed for seamless interaction with humans in diverse domains, yet generating expressive and physically-feasible motions remains a core challenge. We propose a robust and automated pipeline for motion retargeting that enables the generation of natural, stable, and highly expressive motions for a wide variety of humanoid robots using different motion data sources, including noisy pose estimations. To ensure robustness, our approach unifies motions from different kinematic structures into a common canonical rig, systematically refines the motion trajectory to address infeasible poses, enforces foot-contact constraints, and enhances stability. The retargeted motion is then refined to closely follow the source motion while respecting each robot’s physical limits. Through extensive experiments on 12 simulated robots and validation on three real robots, we show that our methodology reliably produces expressive upper-body movements with consistent foot contact. This work represents an important step towards automating robust and expressive motion generation for humanoid robots, enabling deployment in various real-world scenarios.

Details

ICLR Conference 2025 Conference Paper

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

Hyungjoo Chae
Namyoung Kim
Kai Tzu-iunn Ong
Minju Gwak
Gwanwoo Song
Jihoon Kim
Sunghwan Kim 0005
Dongha Lee 0003

Large language models (LLMs) have recently gained much attention in building autonomous agents. However, 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.

Details

NeurIPS Conference 2023 Conference Paper

BubbleML: A Multiphase Multiphysics Dataset and Benchmarks for Machine Learning

Sheikh Md Shakeel Hassan
Arthur Feeney
Akash Dhruv
Jihoon Kim
Youngjoon Suh
Jaiyoung Ryu
Yoonjin Won
Aparna Chandramowlishwaran

In the field of phase change phenomena, the lack of accessible and diverse datasets suitable for machine learning (ML) training poses a significant challenge. Existing experimental datasets are often restricted, with limited availability and sparse ground truth, impeding our understanding of this complex multiphysics phenomena. To bridge this gap, we present the BubbleML dataset which leverages physics-driven simulations to provide accurate ground truth information for various boiling scenarios, encompassing nucleate pool boiling, flow boiling, and sub-cooled boiling. This extensive dataset covers a wide range of parameters, including varying gravity conditions, flow rates, sub-cooling levels, and wall superheat, comprising 79 simulations. BubbleML is validated against experimental observations and trends, establishing it as an invaluable resource for ML research. Furthermore, we showcase its potential to facilitate the exploration of diverse downstream tasks by introducing two benchmarks: (a) optical flow analysis to capture bubble dynamics, and (b) neural PDE solvers for learning temperature and flow dynamics. The BubbleML dataset and its benchmarks aim to catalyze progress in ML-driven research on multiphysics phase change phenomena, providing robust baselines for the development and comparison of state-of-the-art techniques and models.

PDF Details

AAAI Conference 2023 Conference Paper

FLAME: Free-Form Language-Based Motion Synthesis & Editing

Jihoon Kim
Jiseob Kim
Sungjoon Choi

Text-based motion generation models are drawing a surge of interest for their potential for automating the motion-making process in the game, animation, or robot industries. In this paper, we propose a diffusion-based motion synthesis and editing model named FLAME. Inspired by the recent successes in diffusion models, we integrate diffusion-based generative models into the motion domain. FLAME can generate high-fidelity motions well aligned with the given text. Also, it can edit the parts of the motion, both frame-wise and joint-wise, without any fine-tuning. FLAME involves a new transformer-based architecture we devise to better handle motion data, which is found to be crucial to manage variable-length motions and well attend to free-form text. In experiments, we show that FLAME achieves state-of-the-art generation performances on three text-motion datasets: HumanML3D, BABEL, and KIT. We also demonstrate that FLAME’s editing capability can be extended to other tasks such as motion prediction or motion in-betweening, which have been previously covered by dedicated models.

PDF Details DOI

JBHI Journal 2023 Journal Article

WICOX: Weight-Based Integrated Cox Model for Time-to-Event Data in Distributed Databases Without Data-Sharing

Ji A. Park
Tae H. Kim
Jihoon Kim
Yu R. Park

To exploit large-scale biomedical data, the application of common data models and the establishment of data networks are being actively carried out worldwide. However, due to the privacy issues, it is difficult to share data distributed among institutions. In this study, we developed and evaluated weight-based integrated Cox model (WICOX) as a privacy-protecting method without sharing patient-level information across institutions. WICOX generates a weight for each institutional model and builds an integrated model of multi-institutional data based on these weights. WICOX does not require iterative communication until the centralized parameter converges. We performed experiments to show the weight characteristic of our algorithm based on 10 hospitals (2910 intensive care unit (ICU) stays in total) from the electronic intensive care unit Collaborative Research Database to predict time to ICU mortality with eight risk factors. Compared with the centralized Cox model, WICOX showed biases from 0 to 0. 68E-2, from 0. 00E-2 to 4. 98E-2, and from 0. 74E-2 to 1. 7E-2 for time-dependent AUC, log hazard ratio, and survival rate, respectively. In addition, through simulation results using real 10 hospitals, WICOX showed robust results in accuracy under any composition of hospitals. The results of the experiments highlight that WICOX has robust characteristics and provides predictive performance and statistical inference results nearly the same as those of the centralized model. WICOX is a non-iterative method using the weight of institutional model for implementing the Cox model across multiple institutions in a privacy-preserving manner.

Details DOI

NeurIPS Conference 2022 Conference Paper

Simulation-guided Beam Search for Neural Combinatorial Optimization

Jinho Choo
Yeong-Dae Kwon
Jihoon Kim
Jeongwoo Jae
André Hottung
Kevin Tierney
Youngjune Gwon

Neural approaches for combinatorial optimization (CO) equip a learning mechanism to discover powerful heuristics for solving complex real-world problems. While neural approaches capable of high-quality solutions in a single shot are emerging, state-of-the-art approaches are often unable to take full advantage of the solving time available to them. In contrast, hand-crafted heuristics perform highly effective search well and exploit the computation time given to them, but contain heuristics that are difficult to adapt to a dataset being solved. With the goal of providing a powerful search procedure to neural CO approaches, we propose simulation-guided beam search (SGBS), which examines candidate solutions within a fixed-width tree search that both a neural net-learned policy and a simulation (rollout) identify as promising. We further hybridize SGBS with efficient active search (EAS), where SGBS enhances the quality of solutions backpropagated in EAS, and EAS improves the quality of the policy used in SGBS. We evaluate our methods on well-known CO benchmarks and show that SGBS significantly improves the quality of the solutions found under reasonable runtime assumptions.

PDF Details

AAAI Conference 2020 Conference Paper

Visual Domain Adaptation by Consensus-Based Transfer to Intermediate Domain

Jongwon Choi
Youngjoon Choi
Jihoon Kim
Jinyeop Chang
Ilhwan Kwon
Youngjune Gwon
Seungjai Min

We describe an unsupervised domain adaptation framework for images by a transform to an abstract intermediate domain and ensemble classiﬁers seeking a consensus. The intermediate domain can be thought as a latent domain where both the source and target domains can be transferred easily. The proposed framework aligns both domains to the intermediate domain, which greatly improves the adaptation performance when the source and target domains are notably dissimilar. In addition, we propose an ensemble model trained by confusing multiple classiﬁers and letting them make a consensus alternately to enhance the adaptation performance for ambiguous samples. To estimate the hidden intermediate domain and the unknown labels of the target domain simultaneously, we develop a training algorithm using a double-structured architecture. We validate the proposed framework in hard adaptation scenarios with real-world datasets from simple synthetic domains to complex real-world domains. The proposed algorithm outperforms the previous state-of-the-art algorithms on various environments.

PDF Details

ICML Conference 2019 Conference Paper

Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty

Youngjin Kim
Wontae Nam
Hyunwoo Kim 0002
Jihoon Kim
Gunhee Kim

Exploration based on state novelty has brought great success in challenging reinforcement learning problems with sparse rewards. However, existing novelty-based strategies become inefficient in real-world problems where observation contains not only task-dependent state novelty of our interest but also task-irrelevant information that should be ignored. We introduce an information- theoretic exploration strategy named Curiosity-Bottleneck that distills task-relevant information from observation. Based on the information bottleneck principle, our exploration bonus is quantified as the compressiveness of observation with respect to the learned representation of a compressive value network. With extensive experiments on static image classification, grid-world and three hard-exploration Atari games, we show that Curiosity-Bottleneck learns an effective exploration strategy by robustly measuring the state novelty in distractive environments where state-of-the-art exploration methods often degenerate.

Details