Jinliang Zheng's picture

1 4 5

Jinliang Zheng

2toINF

https://2toinf.github.io/

2toINF

AI & ML interests

Computer vision, Multi-modal

Recent Activity

authored a paper 3 days ago

Enhancing Vision-Language Model with Unmasked Token Alignment

authored a paper 3 days ago

MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment

authored a paper 3 days ago

Instruction-Guided Visual Masking

View all activity

Organizations

None yet

2toINF's activity

New activity in 2toINF/UniAct 3 months ago

Improve model card

#1 opened 3 months ago by