4 papers · 1 filter
Whole-Body Conditioned Egocentric Video Prediction
Yutong Bai, Danny Tran, Amir Bar +3
We train models to Predict Ego-centric Video from human Actions (PEVA), given the past video and an action represented by the relative 3D body pose. By conditioning on kinematic po…
Vision-Language Models Create Cross-Modal Task Representations
Grace Luo, Trevor Darrell, Amir Bar
Autoregressive vision-language models (VLMs) can handle many tasks within a single model, yet the representations that enable this capability remain opaque. We find that VLMs align…
Navigation World Models
Amir Bar, Gaoyue Zhou, Danny Tran +2
Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future…
Finding Visual Task Vectors
Alberto Hojel, Yutong Bai, Trevor Darrell +2
Visual Prompting is a technique for teaching models to perform a visual task via in-context examples, without any additional training. In this work, we analyze the activations of M…