Ali Farhadi

is this you? claim profile

∙ 0 followers
University of Washington

Associate Professor at University of Washington

What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions

Learning effective representations of visual data that generalize to a v...
10/16/2020 ∙ by Kiana Ehsani, et al. ∙ 0 ∙ share

read it
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks

Autonomous agents must learn to collaborate. It is not scalable to devel...
07/09/2020 ∙ by Unnat Jain, et al. ∙ 2 ∙ share

read it
In the Wild: From ML Models to Pragmatic ML Systems

Enabling robust intelligence in the wild entails learning systems that o...
07/06/2020 ∙ by Matthew Wallingford, et al. ∙ 13 ∙ share

read it
Supermasks in Superposition

We present the Supermasks in Superposition (SupSup) model, capable of se...
06/26/2020 ∙ by Mitchell Wortsman, et al. ∙ 0 ∙ share

read it
Probing Text Models for Common Ground with Visual Representations

Vision, as a central component of human perception, plays a fundamental ...
05/01/2020 ∙ by Gabriel Ilharco, et al. ∙ 0 ∙ share

read it
Visual Commonsense Graphs: Reasoning about the Dynamic Context of a Still Image

Even from a single frame of a still image, people can reason about the d...
04/22/2020 ∙ by Jae Sung Park, et al. ∙ 14 ∙ share

read it
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform

Visual recognition ecosystems (e.g. ImageNet, Pascal, COCO) have undenia...
04/14/2020 ∙ by Matt Deitke, et al. ∙ 2 ∙ share

read it
Evaluating Machines by their Real-World Language Use

There is a fundamental gap between how humans understand and use languag...
04/07/2020 ∙ by Rowan Zellers, et al. ∙ 0 ∙ share

read it
Grounded Situation Recognition

We introduce Grounded Situation Recognition (GSR), a task that requires ...
03/26/2020 ∙ by Sarah Pratt, et al. ∙ 25 ∙ share

read it
Watching the World Go By: Representation Learning from Unlabeled Videos

Recent single image unsupervised representation learning techniques show...
03/18/2020 ∙ by Daniel Gordon, et al. ∙ 12 ∙ share

read it
Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping

Fine-tuning pretrained contextual word embedding models to supervised do...
02/15/2020 ∙ by Jesse Dodge, et al. ∙ 0 ∙ share

read it
Soft Threshold Weight Reparameterization for Learnable Sparsity

Sparsity in Deep Neural Networks (DNNs) is studied extensively with the ...
02/08/2020 ∙ by Aditya Kusupati, et al. ∙ 3 ∙ share

read it
Artificial Agents Learn Flexible Visual Representations by Playing a Hiding Game

The ubiquity of embodied gameplay, observed in a wide variety of animal ...
12/17/2019 ∙ by Luca Weihs, et al. ∙ 17 ∙ share

read it
Visual Reaction: Learning to Play Catch with Your Drone

In this paper we address the problem of visual reaction: the task of int...
12/04/2019 ∙ by Kuo-Hao Zeng, et al. ∙ 0 ∙ share

read it
What's Hidden in a Randomly Weighted Neural Network?

Training a neural network is synonymous with learning the values of the ...
11/29/2019 ∙ by Vivek Ramanujan, et al. ∙ 78 ∙ share

read it
Conditional Driving from Natural Language Instructions

Widespread adoption of self-driving cars will depend not only on their s...
10/16/2019 ∙ by Junha Roh, et al. ∙ 18 ∙ share

read it
Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index

Existing open-domain question answering (QA) models are not suitable for...
06/13/2019 ∙ by Minjoon Seo, et al. ∙ 0 ∙ share

read it
Butterfly Transform: An Efficient FFT Based Neural Architecture Design

In this paper, we introduce the Butterfly Transform (BFT), a light weigh...
06/05/2019 ∙ by Keivan Alizadeh, et al. ∙ 14 ∙ share

read it
Discovering Neural Wirings

The success of neural networks has driven a shift in focus from feature ...
06/03/2019 ∙ by Mitchell Wortsman, et al. ∙ 2 ∙ share

read it
OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge

Visual Question Answering (VQA) in its ideal form lets us study reasonin...
05/31/2019 ∙ by Kenneth Marino, et al. ∙ 1 ∙ share

read it
Defending Against Neural Fake News

Recent progress in natural language generation has raised dual-use conce...
05/29/2019 ∙ by Rowan Zellers, et al. ∙ 0 ∙ share

read it
HellaSwag: Can a Machine Really Finish Your Sentence?

Recent work by Zellers et al. (2018) introduced a new task of commonsens...
05/19/2019 ∙ by Rowan Zellers, et al. ∙ 0 ∙ share

read it
Two Body Problem: Collaborative Visual Task Completion

Collaboration is a necessary skill to perform tasks that are beyond one ...
04/11/2019 ∙ by Unnat Jain, et al. ∙ 12 ∙ share

read it
Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph

Visual relationship reasoning is a crucial yet challenging task for unde...
03/25/2019 ∙ by Yao-Hung Hubert Tsai, et al. ∙ 0 ∙ share

read it
What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning

Long-term planning poses a major difficulty to many reinforcement learni...
01/06/2019 ∙ by Daniel Gordon, et al. ∙ 12 ∙ share

read it
ELASTIC: Improving CNNs with Instance Specific Scaling Policies

Scale variation has been a challenge from traditional to modern approach...
12/13/2018 ∙ by Huiyu Wang, et al. ∙ 16 ∙ share

read it
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Learning is an inherently continuous phenomenon. When humans learn a new...
12/03/2018 ∙ by Mitchell Wortsman, et al. ∙ 0 ∙ share

read it
From Recognition to Cognition: Visual Commonsense Reasoning

Visual understanding goes well beyond object recognition. With one glanc...
11/27/2018 ∙ by Rowan Zellers, et al. ∙ 30 ∙ share

read it
Visual Semantic Navigation using Scene Priors

How do humans navigate to target objects in novel scenes? Do we use the ...
10/15/2018 ∙ by Wei Yang, et al. ∙ 0 ∙ share

read it
PhotoShape: Photorealistic Materials for Large-Scale Shape Collections

Existing online 3D shape repositories contain thousands of 3D models but...
09/26/2018 ∙ by Keunhong Park, et al. ∙ 2 ∙ share

read it
Label Refinery: Improving ImageNet Classification through Label Progression

Among the three main components (data, labels, and models) of any superv...
05/07/2018 ∙ by Hessam Bagherinezhad, et al. ∙ 0 ∙ share

read it
Actor and Observer: Joint Modeling of First and Third-Person Videos

Several theories in cognitive neuroscience suggest that when people inte...
04/25/2018 ∙ by Gunnar A. Sigurdsson, et al. ∙ 2 ∙ share

read it
Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos

In Actor and Observer we introduced a dataset linking the first and thir...
04/25/2018 ∙ by Gunnar A. Sigurdsson, et al. ∙ 0 ∙ share

read it
Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension

The current trend of extractive question answering (QA) heavily relies o...
04/20/2018 ∙ by Minjoon Seo, et al. ∙ 0 ∙ share

read it
Imagine This! Scripts to Compositions to Videos

Imagining a scene described in natural language with realistic layout an...
04/10/2018 ∙ by Tanmay Gupta, et al. ∙ 2 ∙ share

read it
YOLOv3: An Incremental Improvement

We present some updates to YOLO! We made a bunch of little design change...
04/08/2018 ∙ by Joseph Redmon, et al. ∙ 0 ∙ share

read it
Transferring Common-Sense Knowledge for Object Detection

We propose the idea of transferring common-sense knowledge from source c...
04/03/2018 ∙ by Krishna Kumar Singh, et al. ∙ 2 ∙ share

read it
Who Let The Dogs Out? Modeling Dog Behavior From Visual Data

We introduce the task of directly modeling a visually intelligent agent....
03/28/2018 ∙ by Kiana Ehsani, et al. ∙ 0 ∙ share

read it
AI2-THOR: An Interactive 3D Environment for Visual AI

We introduce The House Of inteRactions (THOR), a framework for visual AI...
12/14/2017 ∙ by Eric Kolve, et al. ∙ 0 ∙ share

read it
IQA: Visual Question Answering in Interactive Environments

We introduce Interactive Question Answering (IQA), the task of answering...
12/09/2017 ∙ by Daniel Gordon, et al. ∙ 0 ∙ share

read it
Structured Set Matching Networks for One-Shot Part Labeling

Diagrams often depict complex phenomena and serve as a good test bed for...
12/05/2017 ∙ by Jonghyun Choi, et al. ∙ 0 ∙ share

read it
Neural Speed Reading via Skim-RNN

Inspired by the principles of speed reading, we introduce Skim-RNN, a re...
11/06/2017 ∙ by Minjoon Seo, et al. ∙ 0 ∙ share

read it
AJILE Movement Prediction: Multimodal Deep Learning for Natural Human Neural Recordings and Video

Developing useful interfaces between brains and machines is a grand chal...
09/13/2017 ∙ by Xin Ru Nancy Wang, et al. ∙ 0 ∙ share

read it
Visual Semantic Planning using Deep Successor Representations

A crucial capability of real-world intelligent agents is their ability t...
05/23/2017 ∙ by Yuke Zhu, et al. ∙ 0 ∙ share

read it
Re3 : Real-Time Recurrent Regression Networks for Visual Tracking of Generic Objects

Robust object tracking requires knowledge and understanding of the objec...
05/17/2017 ∙ by Daniel Gordon, et al. ∙ 0 ∙ share

read it
SeGAN: Segmenting and Generating the Invisible

Objects often occlude each other in scenes; Inferring their appearance b...
03/29/2017 ∙ by Kiana Ehsani, et al. ∙ 0 ∙ share

read it
See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content

Humans have rich understanding of liquid containers and their contents; ...
01/10/2017 ∙ by Roozbeh Mottaghi, et al. ∙ 0 ∙ share

read it
YOLO9000: Better, Faster, Stronger

We introduce YOLO9000, a state-of-the-art, real-time object detection sy...
12/25/2016 ∙ by Joseph Redmon, et al. ∙ 0 ∙ share

read it
Asynchronous Temporal Fields for Action Recognition

Actions are more than just movements and trajectories: we cook to eat an...
12/19/2016 ∙ by Gunnar A. Sigurdsson, et al. ∙ 0 ∙ share

read it
Commonly Uncommon: Semantic Sparsity in Situation Recognition

Semantic sparsity is a common challenge in structured visual classificat...
12/03/2016 ∙ by Mark Yatskar, et al. ∙ 0 ∙ share

read it

Ali Farhadi

Featured Co-authors