News
- [Oct 2024] ReLIC is released on arxiv!
- [Jul 2024] HM3D-OVON accepted at IROS 2024!
- [May 2024] Started as a Research Intern at Meta AI Research Lab.
- [Mar 2024] Awarded the College of Computing Rising Star Doctoral Student Research Award 2023.
- [Feb 2024] 2 papers Seeing the Unseen and GOAT-Bench accepted at CVPR 2024!
- [Jan 2024] Preprint of our paper Seeing the Unseen is out on arXiv!
- [Sep 2023] Serving as a reviewer for ICLR and ICML 2024!
- [Aug 2023] Started PhD in CS at Georgia Tech!
- [May 2023] Started as a Research Intern at Allen Institute of AI (AI2)!
- [Apr 2023] Accepted Georgia Tech CS PhD program offer!
- [Mar 2023] Recived CS PhD program admits from Stanford, Georgia Tech, UT Austin and Simon Fraser University!
- [Mar 2023] Our work HM3DSem is accepted as highlight paper (top 2.5% of submissions) at CVPR 2023!
- [Feb 2023] 2 papers (PIRLNav and HM3DSem) accepted at CVPR, 2023!
- [Jan 2023] Preprint of our paper PIRLNav is out on arXiv!
- [Oct 2022] Preprint of our paper Habitat-Matterport 3D Semantics Dataset is out on arXiv!
- [Oct 2022] Runners-up of the Habitat Challenge 2022 organized at CVPR 2022! Presentation available here
- [May 2022] Interning at Mitsubishi Electric Research Laboratories
- [Apr 2022] Preprint of our paper Offline Visual Representation Learning for Embodied Navigation is out on arXiv!
- [Apr 2022] Awarded the College of Computing Outstanding MS Research Award 2022.
- [Mar 2022] Our paper Habitat-Web accepted at CVPR, 2022!
- [Aug 2021] Joined Georgia Tech for Masters in Computer Science.
- [Jun 2021] Runners-up of the Habitat Challenge 2021 organized at CVPR 2021! Presentation available here.
- [Oct 2020] Represented CloudCV at Google Summer of Code Mentor Summit 2020.
- [Jun 2020] Joined as a Research Intern at Machine Learning and Perception Lab at Georgia Tech to work with Prof. Dhruv Batra & Prof. Devi Parikh.
- [Apr 2020] Served as a Google Summer of Code 2020 Mentor with CloudCV.
- [Nov 2019] Served as a Google Code In 2019 Organization Administrator with CloudCV.
- [Oct 2019] Fabrik accepted at AI systems workshop at SOSP conference.
- [Aug 2019] Started as a Software Development Engineer 2 at Glance.
- [Apr 2019] Served as a Google Summer of Code mentor with CloudCV.
- [Nov 2018] Served as a Google Code In 2018 Mentor with CloudCV.
- [Jul 2018] Started as a Software Development Engineer at Inmobi.
- [May 2018] Selected as a Google Summer of Code student with CloudCV.
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 collaborate with Erik Wijmans and Eric Undersander 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.
During my MS, I was fortunate to intern at Allen Institute of AI (AI2) in Summer 2023 with Luca Weihs and Kuo-Hao Zheng on common-sense and context-based reasoning for embodied agents. At Mitsubishi Electric Research Laborateries (MERL) in Summer 2022 with Anoop Cherian on building embodied agents for navigation and interaction in simulated environments that leverage 3D scene graphs for effective scene understanding.
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.
Publications
ReLIC: A recipe for 64k steps In-Context Reinforcement Learning for Embodied AI
Seeing the Unseen: Visual Common Sense for Semantic Placement
CVPR 2024, VLMNM workshop at ICRA'24
Paper
Code
Website
GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation
HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation
PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav
CVPR 2023, RRL workshop at ICLR 2023
Paper
Code
Website
Habitat-Matterport 3D Semantics Dataset
CVPR 2023 (Highlight, top 2.5% of submissions)
Paper
Website
OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav
arxiv
Paper
Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale
CVPR 2022, EmbodiedAI workshop at CVPR 2022, Overlooked Aspects of IL workshop at RSS 2022 (Spotlight)
Paper
Code
Website
Presentation video
Offline Visual Representation Learning for Embodied Navigation
RRL workshop at ICLR 2023
Paper
Fabrik: An Online Collaborative Neural Network Editor
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.
|