Scholar
Inès Hyeonsu Kim
Google Scholar ID: tBcqfncAAAAJ
KAIST
Citations & Impact
Citations
196
H-index
3
i10-index
3
Publications
9
Co-authors
24
list available
Publications
Resume (English only)
Academic Achievements
- - CVPR 2025: Exploring Temporally-Aware Features for Point Tracking
- - Under-review 2025: Learning to Track Any Points from Human Motion, Pose-dIVE: Pose-Diversified Augmentation for Person Re-Identification, Geomery-Aware Score Distillation via 3D Consistent Noising and Gradient Consistency Modeling
- - ICML 2024: Retrieval-Augmented Score Distillation for Text-to-3D Generation
- - ICLR 2024 (Oral): Diffusion Model for Dense Matching, Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
- - Awards: 2025 Presidential Scholarship, 2025 CVPR Travel Award, 2024 Highest Honors Graduate Award, 2023 Best Paper Award at the 33rd Artificial Intelligence and Signal Processing, IEIE
Research Experience
- - Visiting Researcher at the University of Michigan, Ann Arbor, June - Nov. 2025
- - Research Collaboration at Adobe, San Jose, CA (Remote), Sep. 2024 - present
Education
- M.S. at KAIST AI, advised by Prof. Seungryong Kim, time not explicitly mentioned.
Background
- Research interests include general perception in video, especially point tracking, and its application to 3D/4D video understanding and robotics (Physical AI). Currently an M.S. student at KAIST AI, advised by Prof. Seungryong Kim, and a visiting researcher at the University of Michigan, Ann Arbor, working with Prof. Honglak Lee. Also closely collaborating with Joon-Young Lee and Gabriel Huang at Adobe Research.
Miscellany
- Actively seeking a Ph.D. position to push the boundaries of AI and robotics.
