Ademi Adeniji

I am a Computer Science PhD student at UC Berkeley, advised by Pieter Abbeel. My goal is to develop a generally intelligent agent capable of autonomous learning in the real world. I believe scaling the human physical data footprint is on the critical path to resolving Moravec’s Paradox. Follow me on X for updates on my work.

I received my BS (Honors) and MS in computer science with specialization in artificial intelligence from Stanford University, conducting research under the adivsorship of Fei-Fei Li as well as Kuan Fang and Animesh Garg. I interned at NVIDIA conducting reinforcement learning, robotics, and simulation research mentored by Yuke Zhu and Jim Fan. Before then, I worked on machine learning and automation at Google and digital transformation at McKinsey and Company.

news

Jun 03, 2025	We released our research on tactile robot learning from humans Feel the Force: Contact-Driven Learning from Humans 🤲
May 27, 2025	We released our research on zero-shot human-to-robot learning EgoZero: Robot Learning from Smart Glasses 📝
Oct 10, 2024	I gave an invited talk at Belgium-Netherlands Reinforcement Learning about learning behavior generalists.
Sep 11, 2024	I gave an invited talk at Princeton Reinforcement Learning Lab on learning generalizable policies from action-free data.
Sep 09, 2024	We presented LAMP at RLC!
May 23, 2024	I passed my qualifying exam! Thank you to my committee members Pieter Abbeel, Sergey Levine, Jim Fan, and Ken Goldberg.
Dec 13, 2023	We presented Intrinsic Reward Matching and VIPER and NeurIPS!

publications

Feel the Force: Contact-Driven Learning from Humans

Ademi Adeniji^*, Zhuoran Chen^*, Vincent Liu, Venkatesh Pattabiraman, and 4 more authors

2025

arXiv Bib Blog Code Website

@article{adeniji2025feelforcecontactdrivenlearning,
  title = {Feel the Force: Contact-Driven Learning from Humans},
  author = {Adeniji, Ademi and Chen, Zhuoran and Liu, Vincent and Pattabiraman, Venkatesh and Bhirangi, Raunaq and Haldar, Siddhant and Abbeel, Pieter and Pinto, Lerrel},
  year = {2025},
  eprint = {2506.01944},
  archiveprefix = {arXiv},
  primaryclass = {cs.RO},
  url = {https://arxiv.org/abs/2506.01944},
}

EgoZero: Robot Learning from Smart Glasses

Vincent Liu^*, Ademi Adeniji^*, Haotian Zhan^*, Raunaq Bhirangi, and 2 more authors

2025

arXiv Bib Blog Code Website

@article{liu2025egozerorobotlearningsmart,
  title = {EgoZero: Robot Learning from Smart Glasses},
  author = {Liu, Vincent and Adeniji, Ademi and Zhan, Haotian and Bhirangi, Raunaq and Abbeel, Pieter and Pinto, Lerrel},
  year = {2025},
  eprint = {2505.20290},
  primaryclass = {cs.RO},
  url = {https://arxiv.org/abs/2505.20290},
}

Language Reward Modulation for Pretraining Reinforcement Learning

Ademi Adeniji, Amber Xie, Carmelo Sferrazza, Younggyo Seo, and 2 more authors

In RLC Reinforcement Learning Beyond Rewards Workshop 2024
In RLC Training Agents with Foundation Models Workshop 2024

arXiv Bib Blog Code

@inproceedings{adeniji2023languagerewardmodulationpretraining,
  title = {Language Reward Modulation for Pretraining Reinforcement Learning},
  author = {Adeniji, Ademi and Xie, Amber and Sferrazza, Carmelo and Seo, Younggyo and James, Stephen and Abbeel, Pieter},
  booktitle = {In RLC Reinforcement Learning Beyond Rewards Workshop 2024},
  booktitle2 = {In RLC Training Agents with Foundation Models Workshop 2024},
  year = {2024},
  eprint = {2308.12270},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2308.12270},
}

Video Prediction Models as Rewards for Reinforcement Learning

Alejandro Escontrela^*, Ademi Adeniji^*, Wilson Yan^*, Ajay Jain, and 5 more authors

In NeurIPS 2023

arXiv Bib Blog Code Website

@inproceedings{escontrela2023videopredictionmodelsrewards,
  title = {Video Prediction Models as Rewards for Reinforcement Learning},
  author = {Escontrela, Alejandro and Adeniji, Ademi and Yan, Wilson and Jain, Ajay and Peng, Xue Bin and Goldberg, Ken and Lee, Youngwoon and Hafner, Danijar and Abbeel, Pieter},
  booktitle = {In NeurIPS 2023},
  year = {2023},
  eprint = {2305.14343},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2305.14343},
}

Skill-Based Reinforcement Learning with Intrinsic Reward Matching

Ademi Adeniji^*, Amber Xie^*, and Pieter Abbeel

In RLC Reinforcement Learning Beyond Rewards Workshop 2024 (Spotlight)
In RLC Training Agents with Foundation Models Workshop 2024
In NeurIPS Intrinsically Motivated Open-ended Learning Workshop 2023

Awarded arXiv Bib Blog Code

Spotlight

@inproceedings{adeniji2023skillbasedreinforcementlearningintrinsic,
  title = {Skill-Based Reinforcement Learning with Intrinsic Reward Matching},
  author = {Adeniji, Ademi and Xie, Amber and Abbeel, Pieter},
  booktitle = {In RLC Reinforcement Learning Beyond Rewards Workshop 2024 (Spotlight)},
  booktitle2 = {In RLC Training Agents with Foundation Models Workshop 2024},
  booktitle3 = {In NeurIPS Intrinsically Motivated Open-ended Learning Workshop 2023},
  year = {2023},
  eprint = {2210.07426},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2210.07426},
}

Learning Representations for Unsupervised Skill Discovery

Ademi Adeniji

2021

Advisors: L Fei-Fei, Kuan Fang, Animesh Garg, Yuke Zhu

Bib PDF

@thesis{adeniji2021learningrepresentations,
  title = {Learning Representations for Unsupervised Skill Discovery},
  author = {Adeniji, Ademi},
  school = {Stanford University},
  type = {Undergraduate Honors Thesis},
  year = {2021},
  url = {https://drive.google.com/file/d/1zzUo0O1sdwow0vHvyht7G7ikrbb_nZAH/view?usp=sharing},
  note = {Advisors: L Fei-Fei, Kuan Fang, Animesh Garg, Yuke Zhu}
}

Latent Actor-Critic with Intrinsic Motivation and Skill Hierarchy

Ademi Adeniji, and Eva Zhang

2020

Bib PDF

@thesis{adeniji2020latentactorcritic,
  title = {Latent Actor-Critic with Intrinsic Motivation and Skill Hierarchy},
  author = {Adeniji, Ademi and Zhang, Eva},
  school = {Stanford University},
  type = {Course Project},
  year = {2020},
  url = {https://drive.google.com/file/d/1AnTCsq9rUZF-m9AFBeZEgFjGd4DVO33I/view?usp=sharing},
}

Latent Skill Transfer for Simulated Agents

Ademi Adeniji

2019

Bib PDF

@thesis{adeniji2019latentskilltransfer,
  title = {Latent Skill Transfer for Simulated Agents},
  author = {Adeniji, Ademi},
  school = {Stanford University},
  type = {Course Project},
  year = {2019},
  url = {https://drive.google.com/file/d/1LZmucvSjb3209sNswl-4ZS8mTdGDe_MO/view?usp=sharing},
}

Recurrent Control Nets for Deep Reinforcement Learning

Vincent Liu, Ademi Adeniji, Nate Lee, Jason Zhao, and 1 more author

Stanford Undergraduate Research Journal 2019

arXiv Bib Code

@article{liu2019recurrentcontrolnetsdeep,
  title = {Recurrent Control Nets for Deep Reinforcement Learning},
  author = {Liu, Vincent and Adeniji, Ademi and Lee, Nate and Zhao, Jason and Srouji, Mario},
  journal = {Stanford Undergraduate Research Journal 2019},
  year = {2019},
  eprint = {1901.01994},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/1901.01994},
}

Volumetric Semantic Segmentation of Glioblastoma Tumors from MRI Studies

Ademi Adeniji, and Vincent Liu

2019

Bib PDF Code

@thesis{adeniji2019volumetricsegmentationtumor,
  author = {Adeniji, Ademi and Liu, Vincent},
  title = {Volumetric Semantic Segmentation of Glioblastoma Tumors from MRI Studies},
  school = {Stanford University},
  type = {Course Project},
  year = {2019},
  url = {https://drive.google.com/file/d/11tmPV9PguRXKn-ZWsSea41p-Edo-U3DB/view},
}

Sequence-to-Sequence Generative Argumentative Dialogue Systems with Self-Attention

Ademi Adeniji, Nate Lee, and Vincent Liu

2019

Awarded Bib PDF Code Poster

CS 224N Best Custom Project

@thesis{adeniji2019sequence,
  author = {Adeniji, Ademi and Lee, Nate and Liu, Vincent},
  title = {Sequence-to-Sequence Generative Argumentative Dialogue Systems with Self-Attention},
  school = {Stanford University},
  type = {CS 224N Course Project},
  year = {2019},
  url = {https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1194/reports/custom/15844523.pdf},
}

talks

Reinforcement Learning Behavior Generalists - Top-Down and Bottom-Up
October 2024

I gave an invited talk at Belgium-Netherlands Reinforcement Learning Research. I talk about how reinforcement learning can learn behavior generalists from two opposing perspectives. Here are the slides.

Training Agents using Cheap Data Sources
September 2024

I gave an invited talk at Princeton Reinforcement Learning Lab. I talk about how to leverage cheap action-free data to improve the generalization of reinforcement learning policies. Here are the slides.

Accelerating Reinforcement Learning with Pretrained Behaviors
2022

I gave a series of talks to Preferred Networks, Intel Reinforcement Learning Community, Sony Deep Learning Group, and EA Sports Reinforcement Learning Group. I talk about how to leverage pretrained skills to accelerate reinforcement learning. Here are the slides.