Ikechukwu Daniel Adebi

I am a third-year Ph.D. student in Computer Science at the University of Texas at Austin, currently working under Prof. Mitchell Pryor and Prof. Peter Stone.

My research lies at the intersection of robotics and computer vision, with a focus on robot learning for physically grounded perception and decision-making. I develop learning-based methods that enable robots to understand and reason about world geometry, environment dynamics, and actionable structures for long-horizon planning.

Previously, I received my bachelor’s and master’s degrees from the Massachusetts Institute of Technology studying Computer Science with a focus on Artificial Intelligence.

News

May 27, 2025	Started internship at UT Southwestern Medical Center as a research assistant under Prof. Yang Xie and Prof. Wenqi Shi.
Sep 25, 2024	AMAGO-2 got accepted by NeurIPS 2024!
May 22, 2023	Started internship at IBM Research this summer in Yorktown Heights, NY.
Apr 22, 2023	I was selected to be a GEM Fellow!

Selected Publications

Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video

Daniel Adebi, Sagnik Majumder, and Kristen Grauman

ArXiv Preprint, Feb 2026

Bib PDF Website

@article{adebi2025audiovisualcameraposeestimation,
  title = {Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video},
  author = {Adebi, Daniel and Majumder, Sagnik and Grauman, Kristen},
  year = {2026},
  eprint = {2512.12165},
  journal = {ArXiv Preprint},
  dimensions = {true},
  month = feb
}

AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers

Jake Grisby, Justin Sasek*, Samyak Parajuli*, Daniel Adebi*, Amy Zhang, and Yuke Zhu

NeurIPS, Nov 2024

Bib PDF Code

@article{grigsby2024,
  title = {AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers},
  author = {Grisby, Jake and Sasek*, Justin and Parajuli*, Samyak and Adebi</u>*, <u>Daniel and Zhang, Amy and Zhu, Yuke},
  year = {2024},
  journal = {NeurIPS},
  month = nov,
  dimensions = {true},
}