Computer Science PhD Student
Georgia Tech
abhshkdz at gatech dot edu

Co-founder, Caliper

News


Bio

I am a 4th year Computer Science PhD student at Georgia Tech, advised by Dhruv Batra, and working closely with Devi Parikh. My research focuses on deep learning and its applications in building agents that can see (computer vision), think (reasoning/interpretability), talk (language modeling), and act (reinforcement learning).

My research is supported by fellowships from Facebook, Adobe, and Snap. My CV is available here.

IIT Roorkee
2011 - 2015
Queensland Brain Institute
Summer 2015
Georgia Tech
2017 - Present
Facebook AI Research
S2017, W2018, S2018
DeepMind
W2019

I’ve spent three wonderful semesters as an intern at Facebook AI Research — Summer 2017 and Spring 2018 at Menlo Park, working with Georgia Gkioxari, Devi Parikh and Dhruv Batra on training embodied agents for navigation and question-answering in simulated environments (see embodiedqa.org), and Summer 2018 at Montréal, working with Mike Rabbat and Joelle Pineau on emergent communication protocols in large-scale multi-agent reinforcement learning.

In 2019, I was fortunate to get the opportunity to spend time at DeepMind in London working on grounded language learning with Felix Hill, Laura Rimell, and Stephen Clark, and at Tesla Autopilot in Palo Alto working on differentiable neural architecture search with Andrej Karpathy.

Prior to joining grad school, I worked on neural coding in zebrafish tectum as an intern under Prof. Geoffrey Goodhill and Lilach Avitan at the Goodhill Lab, Queensland Brain Institute.

I graduated from Indian Institute of Technology Roorkee in 2015. During my undergrad years, I’ve been selected twice for Google Summer of Code (2013 and 2014), won several hackathons and security contests (Yahoo! HackU!, Microsoft Code.Fun.Do., Deloitte CCTC 2013 and 2014), and been an active member of SDSLabs.

On the side, I built neural-vqa, an efficient Torch implementation for visual question answering (and its extension neural-vqa-attention), and maintain aideadlin.es (countdowns to a bunch of CV/NLP/ML/AI conference deadlines), and several other side projects (HackFlowy, graf, etc). I also help maintain Erdős, a competitive math learning platform I created during my undergrad. I often tweet, toot, and post pictures from my travels on Instagram and Tumblr.

Blog posts from a previous life.


Publications

Improving Generative Visual Dialog by Answering Diverse Questions

Vishvak Murahari, Prithvijit Chattopadhyay, Dhruv Batra, Devi Parikh, Abhishek Das
EMNLP 2019
Paper Code


Unsupervised Discovery of Decision States for Transfer in Reinforcement Learning

Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra, Ramakrishna Vedantam
ICLR 2019 Task-Agnostic RL Workshop
Paper


TarMAC: Targeted Multi-Agent Communication

Abhishek Das, Théophile Gervet, Joshua Romoff, Dhruv Batra, Devi Parikh, Michael Rabbat, Joelle Pineau
ICML 2019
Paper




Embodied Question Answering in Photorealistic Environments with Point Clouds

Erik Wijmans*, Samyak Datta*, Oleksandr Maksymets*, Abhishek Das, Georgia Gkioxari, Stefan Lee, Irfan Essa, Devi Parikh, Dhruv Batra
CVPR 2019 (Oral)
Paper


Audio-Visual Scene-Aware Dialog

Huda Alamri, Vincent Cartillier, Abhishek Das, Jue Wang, Stefan Lee, Peter Anderson, Irfan Essa, Devi Parikh, Dhruv Batra, Anoop Cherian, Tim K. Marks, Chiori Hori
CVPR 2019
Paper Code video-dialog.com


End-to-end Audio Visual Scene-Aware Dialog Using Multimodal Attention-based Video Features

Chiori Hori, Huda Alamri, Jue Wang, Gordon Wichern, Takaaki Hori, Anoop Cherian, Tim K. Marks, Vincent Cartillier, Raphael Lopes, Abhishek Das, Irfan Essa, Dhruv Batra, Devi Parikh
ICASSP 2019
Paper video-dialog.com


Neural Modular Control for Embodied Question Answering

Abhishek Das, Georgia Gkioxari, Stefan Lee, Devi Parikh, Dhruv Batra
CoRL 2018 (Spotlight)
Paper embodiedqa.org Presentation video


Embodied Question Answering

Abhishek Das, Samyak Datta, Georgia Gkioxari, Stefan Lee, Devi Parikh, Dhruv Batra
CVPR 2018 (Oral)
Paper embodiedqa.org Code Presentation video


Evaluating Visual Conversational Agents via Cooperative Human-AI Games

Prithvijit Chattopadhyay*, Deshraj Yadav*, Viraj Prabhu, Arjun Chandrasekaran, Abhishek Das, Stefan Lee, Dhruv Batra, Devi Parikh
HCOMP 2017
Paper Code


Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning

Abhishek Das*, Satwik Kottur*, Stefan Lee, José M.F. Moura, Dhruv Batra
ICCV 2017 (Oral)
Paper Presentation video


Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra
IJCV 2019, ICCV 2017, NIPS 2016 Interpretable ML for Complex Systems Workshop
Paper Code Demo


Visual Dialog

Abhishek Das, Satwik Kottur, Khushi Gupta, Avi Singh, Deshraj Yadav, José M.F. Moura, Devi Parikh, Dhruv Batra
PAMI 2018, CVPR 2017 (Spotlight)
Paper Code visualdialog.org AMT chat interface Demo Presentation video


Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?

Abhishek Das*, Harsh Agrawal*, C. Lawrence Zitnick, Devi Parikh, Dhruv Batra
CVIU 2017, EMNLP 2016, ICML 2016 Workshop on Visualization for Deep Learning
Paper Project+Dataset neural-vqa-attention


Talks


Side projects

aideadlin.es

aideadlin.es is a webpage to keep track of CV/NLP/ML/AI conference deadlines. It's hosted on GitHub, and countdowns are automatically updated via pull requests to the data file in the repo.

neural-vqa-attention

Torch implementation of an attention-based visual question answering model (Yang et al., CVPR16). The model looks at an image, reads a question, and comes up with an answer to the question and a heatmap of where it looked in the image to answer it. Some results here.

neural-vqa

neural-vqa is an efficient, GPU-based Torch implementation of the visual question answering model from the NIPS 2015 paper 'Exploring Models and Data for Image Question Answering' by Ren et al.

Erdős

Erdős by SDSLabs is a competitive math learning platform, similar in spirit to Project Euler, albeit more feature-packed (support for holding competitions, has a social layer) and prettier.

graf

graf plots pretty git contribution bar graphs in the terminal. gem install graf to install.

HackFlowy

Clone of WorkFlowy.com, a beautiful, list-based note-taking website that has a 500-item monthly limit on the free tier :-(. This project is an open-source clone of WorkFlowy. "Make lists. Not war." :-)

AirMaps

AirMaps was a fun hackathon project that lets users navigate through Google Earth with gestures and speech commands using a Kinect sensor. It was the winning entry in Microsoft Code.Fun.Do.

HackView

Another fun hackathon-winning project built during Yahoo! HackU! 2012 that involves webRTC-based P2P video chat, and was faster than any other video chat provider (at the time, before Google launched Hangouts).

8tracks-downloader

Ugly-looking, but super-effective bash script for downloading entire playlists from 8tracks. (Still works as of 10/2016).