Eui Jun Hwang
Scholar

Eui Jun Hwang

Google Scholar ID: eVEJwL0AAAAJ
Korea Advanced Institute of Science and Technology (KAIST)
Sign Language ProductionSign Language TranslationSelf-Supervised LearningVision-Language
Citations & Impact
All-time
Citations
201
 
H-index
8
 
i10-index
8
 
Publications
20
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings, NeurIPS'25
  • An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs (Oral), NAACL'25
  • A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production, WACV'25
  • PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling, SSL@NeurIPS'24
  • Autoregressive sign language production: A gloss-free approach with discrete representations (Oral), FG'24
  • Preprocessing Mediapipe Keypoints with Keypoint Reconstruction and Anchors for Isolated Sign Language Recognition, RPSL@LREC-COLING'24
  • Leveraging large language models with vocabulary sharing for sign language translation, ICASSPW'23
  • Robot dialog system in the context of hospital receptionist and its demonstration, IJSR'23
  • Sign language production with avatar layering: A critical use case over rare words, LREC'22
  • Non-Autoregressive Sign Language Production with Gaussian Space, BMVC'21
  • Demonstration of hospital receptionist robot with extended hybrid code network to select responses and gestures, ICRA'20
  • Automatic Generation of Eye Expressions with End-to-End Learning, RO-MAN'20
  • Hospital receptionist robot v2: design for enhancing verbal interaction with social skills, Incomplete information
Education
  • PhD student in Computer Science at the Korea Institute of Advanced Science and Technology (KAIST), advisor not specified.
Background
  • PhD student in Computer Science, focusing on vision-language models (VLMs) with a particular interest in applications for sign language and tasks related to long video understanding, including robotics.
Miscellany
  • Personal interests and hobbies are not provided.