Search Results for author: Jihoon Kim

Found 9 papers, 4 papers with code

X-SNS: Cross-Lingual Transfer Prediction through Sub-Network Similarity

no code implementations26 Oct 2023 Taejun Yun, Jinhyeon Kim, Deokyeong Kang, Seong Hoon Lim, Jihoon Kim, Taeuk Kim

Cross-lingual transfer (XLT) is an emergent ability of multilingual language models that preserves their performance on a task to a significant extent when evaluated in languages that were not included in the fine-tuning process.

Cross-Lingual Transfer

Identifying confounders in deep-learning-based model predictions using DeepRepViz

no code implementations27 Sep 2023 Roshan Prakash Rane, Jihoon Kim, Arjun Umesha, Didem Stark, Marc-André Schulz, Kerstin Ritter

For example, experiments on the neuroimaging datasets reveal that sex is a significant confounder in a DL model predicting chronic alcohol users (Con-score=0. 35).

Performance Comparison of Design Optimization and Deep Learning-based Inverse Design

no code implementations23 Aug 2023 Minyoung Jwa, Jihoon Kim, Seungyeon Shin, Ah-hyeon Jin, Dongju Shin, Namwoo Kang

Surrogate model-based optimization has been increasingly used in the field of engineering design.

BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning

3 code implementations27 Jul 2023 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.

Optical Flow Estimation

Learning Joint Representation of Human Motion and Language

no code implementations27 Oct 2022 Jihoon Kim, Youngjae Yu, Seungyoun Shin, Taehyun Byun, Sungjoon Choi

In this work, we present MoLang (a Motion-Language connecting model) for learning joint representation of human motion and language, leveraging both unpaired and paired datasets of motion and language modalities.

Action Recognition Contrastive Learning +2

FLAME: Free-form Language-based Motion Synthesis & Editing

1 code implementation1 Sep 2022 Jihoon Kim, Jiseob Kim, Sungjoon Choi

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.

motion prediction Motion Synthesis

Simulation-guided Beam Search for Neural Combinatorial Optimization

1 code implementation13 Jul 2022 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.

Combinatorial Optimization

Conditional Motion In-betweening

1 code implementation9 Feb 2022 Jihoon Kim, Taehyun Byun, Seungyoun Shin, Jungdam Won, Sungjoon Choi

Motion in-betweening (MIB) is a process of generating intermediate skeletal movement between the given start and target poses while preserving the naturalness of the motion, such as periodic footstep motion while walking.

Pose Prediction

Summary Level Training of Sentence Rewriting for Abstractive Summarization

no code implementations WS 2019 Sanghwan Bae, Taeuk Kim, Jihoon Kim, Sang-goo Lee

As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary.

Abstractive Text Summarization Extractive Text Summarization +3

Cannot find the paper you are looking for? You can Submit a new open access paper.