Scholar
Han Lin
Google Scholar ID: Z9s5gHEAAAAJ
CS PhD Student, UNC
Image/Video Generation
Multimodal Learning
Self-Supervised Learning
LLMs
Efficient Transformers
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
577
H-index
10
i10-index
11
Publications
18
Co-authors
13
list available
Contact
Email
hanlincs@cs.unc.edu
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
4 items
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
2026
Cited
0
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
2026
Cited
0
V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
2026
Cited
0
AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
2026
Cited
0
Resume
Academic Achievements
Published multiple papers at top-tier conferences including NeurIPS, ICLR, ICML, CVPR, ICRA, and COLM
ICLR 2025 Oral: CTRL-Adapter – an efficient and versatile framework for adapting diverse controls to any diffusion model
Three COLM 2024 papers leveraging LLM-guided planning: VideoDirectorGPT, EnvGen, and DiagrammerGPT
CVPR 2023: Supervised Masked Knowledge Distillation for Few-shot Transformers
ICRA 2023: Active Tactile Exploration for 3D Object Recognition
Multiple contributions to scalable Transformers, graph-based integration, random features, and orthogonal Monte Carlo methods
Co-authors
12 total
Mohit Bansal
Parker Distinguished Professor, Computer Science, UNC Chapel Hill
Jaemin Cho
PhD Student at UNC Chapel Hill
Krzysztof Choromanski
Google DeepMind Robotics & Columbia University
Haoxian Chen
Columbia University
Arijit Sehanobish
Postdoctoral Associate, Yale School of Medicine
Guangxing Han
Google DeepMind
Jiawei Phoenix MA
Assistant Professor of Computer Science, City University of Hong Kong
Shih-Fu Chang
Professor of Electrical Engineering and Computer Science, Columbia University