arxiv:2603.18524
Lani Ko
lanikoworld
AI & ML interests
generative models, video diffusion models, world models
Recent Activity
upvoted a paper about 2 hours ago
Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection upvoted a paper about 14 hours ago
Versatile Editing of Video Content, Actions, and Dynamics without Training authored a paper about 20 hours ago
3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation ModelOrganizations
