Probing ViTs

AI & ML interests

We are interested to study the representations learned by Vision Transformers.

Recent Activity

sayakpaul  authored a paper about 8 hours ago

TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models

ariG23498  authored a paper 4 months ago

FineVision: Open Data Is All You Need

sayakpaul  authored a paper 5 months ago

Factuality Matters: When Image Generation and Editing Meet Structured Visuals

View all activity

Team members 2