HourVideo

AI & ML interests

None defined yet.

Recent Activity

keshik6  submitted a paper 7 days ago

Text-to-Image Generative Modeling Without Language Pretraining

ManlingLi  authored a paper 7 months ago

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

ManlingLi  authored a paper 7 months ago

Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

View all activity

Team members 4