activity
20122025
most citedFine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping

215 citations · 411 across the 17 of their papers we have counts for

collaborators
Showing cs.CVShow all

35 papers · 1 filter

cs.CV202219 cited

Retrospectives on the Embodied AI Workshop

Matt Deitke, Dhruv Batra, Yonatan Bisk +36

We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped i…

cs.CV2022

Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents

Yao-Hung Hubert Tsai, Hanlin Goh, Ali Farhadi +1

The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human…

cs.CV2022

Object Manipulation via Visual Target Localization

Kiana Ehsani, Ali Farhadi, Aniruddha Kembhavi +1

Object manipulation is a critical skill required for Embodied AI agents interacting with the world around them. Training agents to manipulate objects, poses many challenges. These…

cs.CV20222 cited

The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents

Sarah Pratt, Luca Weihs, Ali Farhadi

The last few years have witnessed substantial progress in the field of embodied AI where artificial agents, mirroring biological counterparts, are now able to learn from interactio…

cs.CV202154 cited

MERLOT: Multimodal Neural Script Knowledge Models

Rowan Zellers, Ximing Lu, Jack Hessel +5

As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce M…

cs.CV2021

Pushing it out of the Way: Interactive Visual Navigation

Kuo-Hao Zeng, Luca Weihs, Ali Farhadi +1

We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a lim…