312 citations · 615 across the 9 of their papers we have counts for
10 papers · 1 filter
Webly Supervised Concept Expansion for General Purpose Vision Models
Amita Kamath, Christopher Clark, Tanmay Gupta +3
General Purpose Vision (GPV) systems are models that are designed to solve a wide array of visual tasks without requiring architectural changes. Today, GPVs primarily learn both sk…
ManipulaTHOR: A Framework for Visual Object Manipulation
Kiana Ehsani, Winson Han, Alvaro Herrasti +5
The domain of Embodied AI has recently witnessed substantial progress, particularly in navigating agents within their environments. These early successes have laid the building blo…
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
Unnat Jain, Luca Weihs, Eric Kolve +4
Autonomous agents must learn to collaborate. It is not scalable to develop a new centralized agent every time a task's difficulty outpaces a single agent's abilities. While multi-a…
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
Matt Deitke, Winson Han, Alvaro Herrasti +10
Visual recognition ecosystems (e.g. ImageNet, Pascal, COCO) have undeniably played a prevailing role in the evolution of modern computer vision. We argue that interactive and embod…
Learning Generalizable Visual Representations via Interactive Gameplay
Luca Weihs, Aniruddha Kembhavi, Kiana Ehsani +7
A growing body of research suggests that embodied gameplay, prevalent not just in human cultures but across a variety of animal species including turtles and ravens, is critical in…
Two Body Problem: Collaborative Visual Task Completion
Unnat Jain, Luca Weihs, Eric Kolve +5
Collaboration is a necessary skill to perform tasks that are beyond one agent's capabilities. Addressed extensively in both conventional and modern AI, multi-agent collaboration ha…