Jisoo Kim
Scholar

Jisoo Kim

Google Scholar ID: R38A52wAAAAJ
Yonsei university undergradaute student
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
10
 
H-index
1
 
i10-index
0
 
Publications
5
 
Co-authors
0
 
Contact
Emailjisoo6687@yonsei.ac.krGitHubOpen ↗
Publications
5 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Publications:
  • - SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion (Arxiv, 2025)
  • - V.I.P: Iterative Online Preference Distillation for Efficient Video Diffusion Models (ICCV, 2025)
  • - DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding (ICCV, 2025)
  • - Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues (ACL main, 2025)
  • - EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild (NAACL Findings, 2025)
  • - DEEPTalk: Dynamic Emotion Embedding for Probabilistic Speech-Driven 3D Face Animation (AAAI, 2025)
Research Experience
  • Joined LG AI Research as a Research Scientist Intern in September 2025, working on robotics using human demonstrations.
Education
  • Ph.D. student at Yonsei University, Material Science and Engineering, advised by Prof. Youngjae Yu; B.S. degree in Material Science and Engineering from Yonsei University.
Background
  • Research Interests: Human-Aligned AI, focusing on making AI systems that generate, perceive, and reason in a way that enables them to coexist and collaborate with humans.
Co-authors
0 total
Co-authors: 0 (list not available)