SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories Paper • 2503.08625 • Published 3 days ago • 24
MobA: A Two-Level Agent System for Efficient Mobile Task Automation Paper • 2410.13757 • Published Oct 17, 2024 • 33
facebook/wav2vec2-xlsr-53-espeak-cv-ft Automatic Speech Recognition • Updated Dec 10, 2021 • 402k • 30