human object interaction (HOI) video and/or motion generation
levon dang
levondang
AI & ML interests
computer vision, AIGC, multimodal learning, embodied AI
Recent Activity
liked a dataset 17 days ago
imageomics/KABR upvoted a paper about 1 month ago
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning liked a dataset 6 months ago
JeffreyXiang/TRELLIS-500KOrganizations
None yet
models 0
None public yet
datasets 0
None public yet