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

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!