Portrait of Ishika Singh

Ishika Singh

Research Scientist

NVIDIA Cosmos Lab

Profile

Biography

I am a Research Scientist at NVIDIA Cosmos Lab, where I work on generative physical AI and world models for robots. I completed my PhD in Computer Science at USC, advised by Prof. Jesse Thomason. My research interests are across NLP and robotics; primarily around why (how) language is necessary for (can be utilized in) robot learning and embodied AI. I think that problems under Embodied AI are yet more foundational, and hold deep-rooted benefits for the society.

Previously, I was an undergrad at IIT Kanpur, where I worked on topics relating to NLP and theoretical ML with Prof. Ashutosh Modi (IIT Kanpur), and Prof. Pengtao Xie (UC San Diego). I have spent some summers interning at Adobe Research, where I also received Adobe India WIT Scholarship 2020, NVIDIA Robotics Research, and Amazon Frontier AI and Robotics. I was also selected as a member of the RSS Pioneers 2025 Cohort.

Research interests

  • Robot Learning
  • 3D Representation Learning
  • Embodied AI
  • World Models for Physical AI

Education

  1. PhD, Computer Science, 2021–2026

    University of Southern California, LA, CA

  2. B.Tech., double major in Computer Science and Chemical Engineering, 2016–2021

    Indian Institute of Technology Kanpur, India

News & service

Updates

  1. Joined NVIDIA Cosmos Lab. Super excited to build generative physical AI for robots!

  2. OG-VLA accepted to IROS 2026!

  3. Passed thesis defense at USC!

  4. Passed thesis proposal at USC!

  5. Selected as a member of the RSS Pioneers Cohort 2025!!!

  6. I will be interning at Amazon Frontier AI and Robotics, San Francisco in Summer'25!

  7. Passed qualification exam at USC and upgraded to being a PhD candidate!

  8. Invited panelist in 2024 Beyond the Ph.D. and Postdoctoral Career Conference, USC.

  9. Published Language Models meet Classical Planners to make smarter Robot Task Plans in the USC RASC blog.

  10. The Colosseum is accepted to RSS 2024 and is open-source now!

  11. Interviewed for ProgPrompt for a Scientific American article!

  12. Released The Colosseum: A Benchmark for Evaluating Generalization for Robotic Manipulation.

  13. Selected as Finalist for the Qualcomm Innovation Fellowship with Jesse Zhang!

  14. I will be interning again at NVIDIA SRL in Summer'24 with Valts and Animesh!!

  15. I received RAS Travel Grant to attend ICRA 2023.

  16. Self-supervised 3D representation learning is accepted to Pretraining4Robotics workshop @ ICRA 2023.

  17. ProgPrompt is accepted to ICRA 2023 and AuRo Journal.

  18. I will be interning at NVIDIA AI Robotics Research Lab, Seattle in Summer'22, advised by Valts and Animesh!

  19. Work on Interactive Fiction Games accepted as extended abstract at AAMAS'22. [arXiv].

  20. Joined the CS PhD program at USC as a member in the GLAMOR Lab with 1 year of USC Grad Fellowship!

  21. Work on Affective Text Generation accepted as long paper at COLING'20. [arXiv]

  22. Adobe released a blog on my internship at Adobe Research, India! [Read here]

  23. Work on Differentially-private Federated Neural Architecture Search accepted at FL-ICML'20. [arXiv]

  24. Received Adobe India WIT Scholarship 2020! [Adobe’s Blog][Getting-through-it Advice]

Academic service

  1. Co-organizing the Workshop on Human-Robot Dialogue at IROS 2026.

  2. Co-organizing From Data to Decisions: VLA Pipelines for Real Robots, ICRA 2026.

  3. Serving as Program Committee Chair, RSS Pioneers 2026, RSS 2026. Looking forward to all the prospective applications!

  4. Co-organizing SemRob Workshop, RSS 2025.

  5. Co-organizing 3D VLMs for Robotics, CVPR 2025.

  6. Co-organizing Language and Robot Learning Workshop, CoRL 2024.

  7. Co-organizing vision-and-dialogue TEACh TATC Challenge @ Embodied AI Workshop, CVPR'22 and CVPR'23.

Research

Selected publications

Full list on Google Scholar.

Overview graphic for generalized robot reasoning and control

RSS Pioneers 2025

Adapting Large Pre-Trained Models for Generalized Robot Reasoning and Control

Ishika Singh

Robotics: Science and Systems Pioneers (RSS Pioneers) 2025

OG-VLA model overview

IROS 2026

OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation

Ishika Singh, Ankit Goyal, Stan Birchfield, Dieter Fox, Animesh Garg, Valts Blukis

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026

ProgPrompt task planning example

ICRA · AuRo 2023

ProgPrompt: Generating Situated Robot Task Plans using Large Language Models

Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, Animesh Garg

International Conference on Robotics and Automation (ICRA) 2023

Also at LaReL @ NeurIPS 2022, LangRob @ CoRL 2022

Extended version in Autonomous Robots (AR) 2023 (Large Language Models in Robotics)

Example from research on playing text-based games

AAMAS 2022

Pre-trained Language Models as Prior Knowledge for Playing Text-based Games

Ishika Singh, Gargi Singh, Ashutosh Modi

International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2022 (Extended Abstracts)

Controlled affective text generation model

COLING 2020

Adapting a Language Model for Controlled Affective Text Generation

Ishika Singh*, Ahsan Barkati*, Tushar Goswamy, Ashutosh Modi

International Conference on Computational Linguistics (COLING) 2020

Also at Wordplay: When Language Meets Games @ NeurIPS 2020

Get in touch

Contact

Email ishikasingh95@gmail.com
Office NVIDIA, Santa Clara, CA
Twitter DM