JiankangDeng
JiankangDeng
AI & ML interests
multi-modal foundation models and generative modeling of the physical world
Recent Activity
upvoted
a
paper
30 days ago
LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal
Training
upvoted
a
paper
3 months ago
Region-based Cluster Discrimination for Visual Representation Learning
authored
a paper
9 months ago
RealSyn: An Effective and Scalable Multimodal Interleaved Document
Transformation Paradigm
Organizations
