Scholar
Donggyun Kim
Google Scholar ID: g_CtB50AAAAJ
Phd. Student at KAIST
Citations & Impact
Citations
162
H-index
5
i10-index
4
Publications
8
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- Recent publications include:
- - "Universal Few-shot Spatial Control for Diffusion Models" (NeurIPS, 2025)
- - "HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning" (arXiv preprint, 2025)
- - "AdaRank: Adaptive Rank Pruning for Enhanced Model Merging" (arXiv preprint, 2025)
- - "Revisiting weight averaging for model merging" (arXiv preprint, 2024)
- - "Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control" (NeurIPS, 2024)
- - "Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild" (ECCV, 2024)
- - "Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching" (ICLR, 2023)
- - "Multi-Task Neural Processes" (ICLR, 2022)
- - "High-Fidelity Synthesis with Disentangled Representation" (ECCV, 2020)
Research Experience
- Currently a visiting scholar at the NYU Global AI Frontier Lab in New York, collaborating with Professor Mengye Ren.
Education
- PhD - KAIST School of Computing, Advisor: Professor Seunghoon Hong
Background
- PhD student at KAIST School of Computing, supervised by Professor Seunghoon Hong. Current research interest is few-shot learning and general-purpose AI. Particularly interested in building a generalist model to solve various tasks without heavy task-specific training.
