Utkarsh Mishra(@utkarshm0410):WAMs are popular because of their promise of better generalization. Is that true? We started playing with Video-Action-Model (VAMs) and realized a gap: video model backbones can compositionally generalize but VAMs often do not. We coin this the Video-Action-Generalization (VAG) gap and present a study on how to explain and improve it. More details: https://t.co/kwoxy2SCVu 🧵 below

Utkarsh Mishra

@utkarshm0410

Intern@Nvidia SRL, Robotics PhD Student @GeorgiaTech || Prev. intern at Amazon FAR, TRI|| Robot Learning || IITR'21 || 🎸🎢🤖|| He/Him || views are mine.

参加 July 2015

731 フォロー中 629 ファン

Utkarsh Mishra@utkarshm0410

2026.07.10 19:15

WAMs are popular because of their promise of better generalization. Is that true? We started playing with Video-Action-Model (VAMs) and realized a gap: video model backbones can compositionally generalize but VAMs often do not. We coin this the Video-Action-Generalization (VAG) gap and present a study on how to explain and improve it. More details: 🧵 below