A unified mask-token interface for MLLMs.
zhou yikang
zhouyik
AI & ML interests
None yet
Recent Activity
liked
a Space
about 15 hours ago
insomnia7/SAMTok
authored
a paper
about 15 hours ago
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries
authored
a paper
about 15 hours ago
Are They the Same? Exploring Visual Correspondence Shortcomings of
Multimodal LLMs
Organizations
None yet