Ram Ramrakhya (original) (raw)

News

Bio

I am a second year PhD student in the department of Computer Science at Georgia Tech advised by Prof. Dhruv Batra and Prof. Zsolt Kira. Prior to this, I completed my Masters in CS at Georgia Tech advised by Prof. Dhruv Batra and Abhishek Das. I also closely collaborated with Erik Wijmans during my time as a MS student.

I am interested in building general purpose home robots that can operate in real world environments. To advance this goal, I am interested in scaling robot learning data via cheaper, safer, and scalable alternative sources like: (a.) 3D Simulation: a safe, inexpensive, and scalable way to gather human teleoperation data and establish fundamental benchmarks for embodied tasks, and (b) Synthetic Data: which involves curating embodied data by automatically annotating unlabelled web data using vision-and-language foundation models as annotators.

Apple ML Research
Spring 2025

Meta AI Research
Summer 2024

Allen Insitute of AI (AI2)
Summer 2023

Mitsubishi Electric Research Laborateries
Summer 2022

Georgia Tech
2021 - Current

Pune Institute of Computer Technology
2015 - 2018

I am interning at Apple MLR with Alexander Toshev since Spring 2025. I was an intern at Meta FAIR from Summer to Winter 2024 working with Roozbeh Mottaghi. During my MS, I was fortunate to intern at Allen Institute of AI (AI2) in Summer 2023 with Luca Weihs and Kuo-Hao Zheng. In 2022, I was an intern at Mitsubishi Electric Research Laborateries (MERL) with Anoop Cherian.

Previously, I spent a year working as a Research Intern in Computer Vision and Machine Learning Perception Lab at Georgia Tech advised by Prof. Dhruv Batra and Prof. Devi Parikh. I also lead an open source organization, CloudCV, where we are building several open-source softwares for reproducible AI research.

If you have any questions / want to collaborate / discuss research, feel free to send me an email at ram.ramrakhya@gatech.edu.

Selected Publications

Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning

Under review Paper Website

GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation

Mukul Khanna*, Ram Ramrakhya*, Gunjan Chhablani, Sriram Yenamandra, Theophile Gervet, Matthew Chang, Zsolt Kira, Devendra Singh Chaplot, Dhruv Batra, Roozbeh Mottaghi
CVPR 2024 Paper Code Website

Seeing the Unseen: Visual Common Sense for Semantic Placement

Ram Ramrakhya, Aniruddha Kembhavi, Dhruv Batra, Zsolt Kira, Kuo-Hao Zeng^, Luca Weihs^
CVPR 2024, VLMNM workshop at ICRA'24 Paper Code Website

PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav

Ram Ramrakhya, Dhruv Batra, Erik Wijmans, Abhishek Das
CVPR 2023, RRL workshop at ICLR 2023 Paper Code Website

Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale

Ram Ramrakhya, Eric Undersander, Dhruv Batra, Abhishek Das
CVPR 2022, EmbodiedAI workshop at CVPR 2022, Overlooked Aspects of IL workshop at RSS 2022 (Spotlight) Paper Code Website Presentation video

All Publications

PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks

Matthew Chang, Gunjan Chhablani, Alexander Clegg, Mikael Dallaire Cote, Ruta Desai, Michal Hlavac, Vladimir Karashchuk, Jacob Krantz, Roozbeh Mottaghi, Priyam Parashar, Siddharth Patki, Ishita Prasad, Xavier Puig, Akshara Rai, Ram Ramrakhya, Daniel Tran, Joanne Truong, John M. Turner, Eric Undersander, Tsung-Yen Yang
ICLR 2025 Website Paper Code

ReLIC: A recipe for 64k steps In-Context Reinforcement Learning for Embodied AI

Ahmad Elawady, Gunjan Chhablani, Ram Ramrakhya, Karmesh Yadav, Dhruv Batra, Zsolt Kira, Andrew Szot
Under review Paper Code

HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation

Naoki Yokoyama*, Ram Ramrakhya*, Abhishek Das, Dhruv Batra, Sehoon Ha
IROS'24 Paper Code Website

Habitat-Matterport 3D Semantics Dataset

Karmesh Yadav*, Ram Ramrakhya*, Santhosh Kumar Ramakrishnan*, Theo Gervet, John Turner, Aaron Gokaslan, Noah Maestre, Angel Xuan Chang, Dhruv Batra, Manolis Savva, Alexander William Clegg^, Devendra Singh Chaplot^
CVPR 2023 (Highlight, top 2.5% of submissions) Paper Website

OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav

Karmesh Yadav*, Arjun Majumdar*, Ram Ramrakhya, Naoki Yokoyama, Aleksei Baevski, Zsolt Kira, Oleksandr Makysmets, Dhruv Batra
arxiv Paper

Offline Visual Representation Learning for Embodied Navigation

Karmesh Yadav, Ram Ramrakhya, Arjun Majumdar, Vincent-Pierre Berges, Sachit Kuhar, Dhruv Batra, Aleksei Baevski, Oleksandr Makysmet
RRL workshop at ICLR 2023 Paper

Fabrik: An Online Collaborative Neural Network Editor

Utsav Garg, Viraj Prabhu, Deshraj Yadav, Ram Ramrakhya, Harsh Agarwal, Dhruv Batra
Workshop on AI Systems, SOSP'2019 Paper Code

Projects

EvalAI

Leading open source platform for evaluating and benchmarking AI models. We have hosted 200+ AI challenges with 18,000+ users, who have created 180,000+ submissions. More than 30 organizations from industry and academia use it for hosting their AI challenges. The project is open source with 130+ contributors, and 2M+ yearly pageviews. Some of the organizations using it are Google Research, Facebook AI Research, DeepMind, Amazon, eBay Research, Mapillary Research, etc. and research labs from MIT, Stanford, Carnegie Mellon University, Georgia Tech, Virginia Tech, UMBC, University of Pittsburg, Draper, University of Adelaide, IIT-Madras, Nankai University, etc. also use it to host large AI challenges like AlexaPrize on it. It's forked versions are used by large organizations such as World Health Organization, Forschungszentrum Jülich (one of the largest interdisciplinary research centres in Europe), etc. for hosting their challenges instead of reinventing the wheel.

Fabrik

Fabrik is an online collaborative platform to build, visualize and train deep learning models via a simple drag-and-drop interface. It allows researchers to collectively develop and debug models using a web GUI that supports importing, editing and exporting networks to popular frameworks like Caffe, Keras, and TensorFlow.