arxiv:2507.06543
Dongyoon Han
calintz
AI & ML interests
SOTA modeling, VM, VLM, LLM, and all machine learning things
Recent Activity
upvoted
a
paper
1 day ago
MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model
upvoted
a
paper
4 months ago
RL makes MLLMs see better than SFT
upvoted
a
paper
4 months ago
Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs