Scholar
Hyelin Nam
Google Scholar ID: k6nzq08AAAAJ
University of Michigan
Citations & Impact
Citations
116
H-index
4
i10-index
2
Publications
9
Co-authors
0
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Paper [P2] Generating Human Motion Videos using a Cascaded Text-to-Video Framework, arxiv, 2025
- Paper [P1] Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs, arxiv, 2025
- Paper [C6] VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling, ICCV, 2025
- Paper [C5] SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering, ICCV, 2025
- Paper [C4] Optical-Flow Guided Prompt Optimization for Coherent Video Generation, CVPR, 2025
- Paper [C3] CFG++: Manifold-constrained Classifier Free Guidance For Diffusion Models, ICLR, 2025, Silver prize, 31st Samsung Humantech Paper Award
- Paper [C2] Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing, CVPR, 2024
- Paper [C1] HairFIT: Pose-invariant Hairstyle Transfer via Flow-based Hair Alignment and Semantic-region-aware Inpainting, BMVC, 2022, Best Paper Award, Korean Artificial Intelligence Association, 2021
Background
- Research Interests: Diffusion models, Generative models. Goal is to advance generative models to accurately capture real-world dynamics, ultimately enabling them to function as reliable real-world priors.
Co-authors