Sangmin Han

Sang-Min-i

·

sangmin213

AI & ML interests

None yet

Recent Activity

upvoted a paper 11 days ago

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

upvoted a paper 11 days ago

Video-Oasis: Rethinking Evaluation of Video Understanding

upvoted a paper 20 days ago

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

View all activity

Organizations

None yet

liked 3 models 5 months ago

Qwen/Qwen-Image-2512

Text-to-Image • 20B • Updated Dec 31, 2025 • 49.9k • • 909

black-forest-labs/FLUX.2-klein-9B

Image-to-Image • 9B • Updated Feb 24 • 327k • • 1.08k

black-forest-labs/FLUX.2-klein-4B

Image-to-Image • 4B • Updated Feb 24 • 379k • • 807