Junfei Wu's picture

2 15 5

Junfei Wu

Hyperwjf

·

Hyperwjf

AI & ML interests

None yet

Recent Activity

upvoted a paper 5 days ago

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing

updated a dataset 15 days ago

AntResearchNLP/ViLaVT-Data-HF

published a dataset 18 days ago

AntResearchNLP/ViLaVT-Data-HF

View all activity

Organizations

New activity in prithivMLmods/Multimodal-VLM-v1.0 5 months ago

Friendly note: ViLaSR relies on thinking with images, but the demo uses text-only reasoning

#4 opened 5 months ago by

New activity in lmms-lab/LLaVA-OneVision-Data 8 months ago

Are there only single images?

#6 opened over 1 year ago by