Currently making GPUs go burrrrr..... 👩‍💻!


Before that, I worked as a Research Engineer at Meta Fundamental Artificial Intelligence Research (FAIR) NYC with the mission of building foundation models for multimodal data. Prior to that, I was an AI Resident at Meta FAIR London where I explored ideas to improve systematic generalization of Reinforcement Learning agents with Roberta Raileanu and Tim Rocktäschel. I have also spent a wonderful year at Carnegie Mellon University writing my undergraduate thesis under Katerina Fragkiadaki on topics in 3D Computer Vision and Language Grounding. I completed my undergraduate studies at BITS Pilani, majoring in Computer Science.

Updates

  • Two papers accepted to ICLR 2024! See you in Vienna 🇦🇹!
  • My first project on Open-Ended Learning from Meta AI has been accepted to CoLLAs 2023!
  • BeautyDETR accepted to ECCV 2022!
  • September 2021: Started my residency at FAIR (Meta AI)!
  • 2 papers accepted for Oral Presentation at IJCNN 2021!
  • CoCoNets accepted to CVPR 2021!
  • Joined Prof. Katerina's lab at CMU as an intern!
  • Interned with Prof. Christophe Dessimoz, UNIL during Summers 2020
  • Attended Google Research India's AI Summer School (Computer Vision track) from August 20-22, 2020

Publications


The Generalization Gap in Offline Reinforcement Learning

Ishita Mediratta*, Qingfei You*, Minqi Jiang, Roberta Raileanu
ICLR 2024

Understanding the Effects of RLHF on LLM Generalisation and Diversity

Robert Kirk, Ishita Mediratta, Christoforos Nalmpantis, Jelena Luketina, Eric Hambro, Edward Grefenstette, Roberta Raileanu
ICLR 2024

Stabilizing Unsupervised Environment Design with a Learned Adversary

Ishita Mediratta, Minqi Jiang*, Jack Parker-Holder*, Michael Dennis, Eugene Vinitsky, Tim Rocktäschel (* = Equal Contribution)
CoLLAs 2023
Oral Presentation

Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds

Ayush Jain*, Nikolaos Gkanatsios*, Ishita Mediratta, Katerina Fragkiadaki (* = Equal Contribution)
ECCV 2022

CoCoNets: Continuous Contrastive 3D Scene Representations

Shamit Lal*, Mihir Prabhudesai*, Ishita Mediratta, Adam W. Harley, Katerina Fragkiadaki (* = Equal Contribution)
CVPR 2021

LipARELU: A-ReLU Networks aided by Lipschitz Acceleration

Ishita Mediratta, Snehanshu Saha, Shubhad Mathur
IJCNN 2021
Oral Presentation

A Reduced-scale Cortical Network with Izhikevich's Neurons on SpiNNaker

Chinmay Chiplunkar, Nishant Gautam, Ishita Mediratta, Andrew Gait, Sujith Thomas, Andrew Rowley, Teresa Serrano-Gotarredona, Basabdatta Sen-Bhattacharya
IJCNN 2021
Oral Presentation

OMA orthology in 2021: website overhaul, conserved isoforms, ancestral gene order and more

Adrian M Altenhoff, Clément-Marie Train, Kimberly J Gilbert, Ishita Mediratta, Tarcisio Mendes de Farias, David Moi, Yannis Nevers, Hale-Seda Radoykova, Victor Rossier, Alex Warwick Vesztrocy, Natasha M Glover, Christophe Dessimoz
Nucleic Acids Research, 2020