Video & Image Sense Lab

AI & ML interests

None defined yet.

Recent Activity

lmsdss  authored a paper 38 minutes ago

QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain

lmsdss  authored a paper 38 minutes ago

IPO: Interpretable Prompt Optimization for Vision-Language Models

lmsdss  authored a paper 38 minutes ago

RegionReasoner: Region-Grounded Multi-Round Visual Reasoning

View all activity

Papers

LiFT: Loop Flow Transformers

View all Papers

Team members 12