Web
  Analytics
Aniruddha (Ani) Kembhavi

Aniruddha (Ani) Kembhavi


I lead PRIOR, the computer vision team at the Allen Institute for AI (AI2) in sunny Seattle. I am also an Affiliate Associate Professor at the Computer Science & Engineering department at the University of Washington.

Prior to AI2, I spent five enjoyable years at Microsoft Bing, building large scale machine learning systems in the Image & Video Search Relevance team.

I grew up in Pune, India where I obtained by Bachelors in Engineering at the College Of Engineering Pune (COEP). I got my Ph.D. at the University of Maryand, College Park under the supervision of Prof. Larry S. Davis.

I am particularly interested in research problems at the intersection of vision, language and embodiment.

Email  /  Google Scholar  /  Semantic Scholar  /  Twitter

profile photo
Hiring

PRIOR is looking to hire highly motivated Research Scientists, Research Engineers, PostDocs and Pre-Doctoral Candidates.
We consider applications on a rolling basis.

News

Sep 2020 2 papers accepted to Neurips 2020: Learning from Interaction and Supermasks.
Sep 2020 X-LXMERT has been accepted to EMNLP. Check out the new demo and webpage.
Aug 2020 AllenAct (BETA) has been released! Check out the webpage and github repo.
Apr 2020 2 papers accepted to ECCV 2020 (Both Spotlights): CordialSYNC and Grounded Situations
Apr 2020 2 papers accepted to CVPR 2020: RoboTHOR and Hidden Networks
Feb 2020 RoboTHOR Challenge announced! Check it out here.
Feb 2020 Check out the Computer Vision Explorer here. Lots of demos for diverse computer vision tasks.
Apr 2019 2 papers (both Oral presentations) accepted to CVPR 2019: Two Body Problem and Elastic

Research

X-LXMERT: Paint, Caption and Answer Questionswith Multi-Modal Transformers
Jaemin Cho, Jiasen Lu, Dustin Schwenk, Hannaneh Hajishirzi, Aniruddha Kembhavi
EMNLP 2020

PDF / Project Page / Demo

Learning About Objects by Learning to Interact with Them
Martin Lohmann, Jordi Salvador, Aniruddha Kembhavi, Roozbeh Mottaghi
Neurips 2020

PDF

Supermasks in Superposition
Mitchell Wortsman, Vivek Ramanujan, Rosanne Liu, Aniruddha Kembhavi, Mohammad Rastegari, Jason Yosinski, Ali Farhadi
Neurips 2020

PDF / Blog post

AllenAct: A Framework for Embodied AI Research
Luca Weihs, Jordi Salvador, Klemen Kotar, Unnat Jain, Kuo-Hao Zeng, Roozbeh Mottaghi, Aniruddha Kembhavi
Arxiv 2020

PDF / Project Page / Code

A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
Unnat Jain, Luca Weihs, Eric Kolve, Ali Farhadi, Svetlana Lazebnik, Aniruddha Kembhavi, Alexander Schwing
ECCV 2020  [Spotlight Presentation]

PDF / Project Page / Code / Teaser Video / Detailed Video

Grounded Situation Recognition
Sarah Pratt, Mark Yatskar, Luca Weihs, Ali Farhadi, Aniruddha Kembhavi
ECCV 2020  [Spotlight Presentation]

PDF / Project Page / Code

Bridging the Imitation Gap by Adaptive Insubordination
Luca Weihs, Unnat Jain, Jordi Salvador, Svetlana Lazebnik, Aniruddha Kembhavi, Alexander Schwing
Arxiv 2020

PDF / Project Page

In the Wild: From ML Models to Pragmatic ML Systems
Matthew Wallingford, Aditya Kusupati, Keivan Alizadeh-Vahid, Aaron Walsman, Aniruddha Kembhavi, Ali Farhadi
Arxiv 2020

PDF / Project Page / Code

ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
Dhruv Batra, Aaron Gokaslan, Ani Kembhavi, Oleksandr Maksymets, Roozbeh Mottaghi, Manolis Savva, Alexander Toshev, Erik Wijmans
Arxiv 2020

PDF

RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
Matt Deitke*, Winson Han*, Alvaro Herrasti*, Aniruddha Kembhavi*, Eric Kolve*, Roozbeh Mottaghi*, Jordi Salvador*, Dustin Schwenk*, Eli VanderBilt*, Matthew Wallingford*, Luca Weihs*, Mark Yatskar*, Ali Farhadi
CVPR 2020

PDF / Project Page

What’s Hidden in a Randomly Weighted Neural Network?
Vivek Ramanujan, Mitchell Wortsman, Aniruddha Kembhavi, Ali Farhadi, Mohammad Rastegari
CVPR 2020

PDF

Artificial Agents Learn Flexible Visual Representations by Playing a Hiding Game
Luca Weihs, Aniruddha Kembhavi, Winson Han, Alvaro Herrasti, Eric Kolve, Dustin Schwenk, Roozbeh Mottaghi, & Ali Farhadi
Arxiv 2019

PDF

Two Body Problem: Collaborative Visual Task Completion
Unnat Jain, Luca Weihs, Eric Kolve, Mohammad Rastegari, Svetlana Lazebnik, Ali Farhadi, Alexander Schwing, Aniruddha Kembhavi
CVPR 2019  [Oral Presentation]

PDF / Project Page / Video

ELASTIC: Improving CNNs with Instance Specific Scaling Policies
Huiyu Wang, Aniruddha Kembhavi, Ali Farhadi, Alan Yuille, Mohammad Rastegari
CVPR 2019  [Oral Presentation]

PDF / Project Page

Imagine This! Scripts to Compositions to Videos
Tanmay Gupta, Dustin Schwenk, Ali Farhadi, Derek Hoiem, Aniruddha Kembhavi
ECCV 2018

PDF / Project Page / Video

IQA: Visual Question Answering in Interactive Environments
Daniel Gordon, Aniruddha Kembhavi, Mohammad Rastegari, Joseph Redmon, Dieter Fox, Ali Farhadi
CVPR 2018

PDF / Project Page / Video

Structured Set Matching Networks for One-Shot Part Labeling
Jonghyun Choi, Jayant Krishnamurthy, Aniruddha Kembhavi, Ali Farhadi
CVPR 2018  [Spotlight Presentation]

PDF / Project Page

Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering
Aishwarya Agrawal, Dhruv Batra, Devi Parikh, Aniruddha Kembhavi
CVPR 2018

PDF

Are You Smarter Than A Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension
Aniruddha Kembhavi, Minjoon Seo, Dustin Schwenk, Jonghyun Choi, Ali Farhadi, Hannaneh Hajishirzi
CVPR 2017  [Spotlight Presentation]

PDF / Project Page

Bidirectional Attention Flow for Machine Comprehension
Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, Hannaneh Hajishirzi
ICLR 2017

PDF / Project Page / Code

A diagram is worth a dozen images
Aniruddha Kembhavi, Mike Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi
ECCV 2016

PDF / Project Page

Semantic Parsing to Probabilistic Programs for Situated Question Answering
Jayant Krishnamurthy, Oyvind Tafjord, Aniruddha Kembhavi
EMNLP 2016  [Oral Presentation]

PDF / Code

Vehicle detection using partial least squares
Aniruddha Kembhavi, David Harwood, Larry S Davis
TPAMI 2011

PDF

Why did the person cross the road (there)? scene understanding using probabilistic logic models and common sense reasoning
Aniruddha Kembhavi, Tom Yeh, Larry S Davis
ECCV 2010

PDF

Observing human-object interactions: Using spatial and functional compatibility for recognition
Abhinav Gupta, Aniruddha Kembhavi, Larry S. Davis
TPAMI 2009

PDF

Human detection using partial least squares analysis
William Robson Schwartz, Aniruddha Kembhavi, Larry S. Davis
ICCV 2009  [Oral Presentation]

PDF

Scene it or not? incremental multiple kernel learning for object detection
Aniruddha Kembhavi, Behjat Siddiquie, Roland Miezianko, Scott McCloskey, Larry S. Davis
ICCV 2009

PDF

Resource Allocation for Tracking Multiple Targets Using Particle Filters
Aniruddha Kembhavi, William Robson Schwartz, Larry S. Davis
Workshop on Visual Surveillance held in conjunction with ECCV 2008

PDF

Tracking Down Under: Following the Satin Bowerbird
Aniruddha Kembhavi, Ryan Farrell, Yuancheng Luo, David Jacobs, Ramani Duraiswami, Larry S. Davis
Workshop on Applications of Computer Vision (WACV) 2008  [Oral Presentation]

PDF

Press Coverage
X-LXMERT: Teaching vision-and-language transformer models to paint

AllenAct: An open source framework for research in Embodied AI

AI & Creativity

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

Iconary: An AI powered drawing and guessing game

Craft: Scripts to Compositions to Videos

Credit

This website's source code was adapted from Jon Barron. Thanks for this elegant template Jon!