agentstudio

AI & ML interests

None defined yet.

Recent Activity

zixianma  authored a paper about 2 months ago

SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality

zixianma  authored a paper about 2 months ago

m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks

zixianma  authored a paper about 2 months ago

Task Me Anything

View all activity

Team members 9