Feryal Behbahani

Research Scientist, DeepMind

Joined

August 2018

Names

Feryal Behbahani (Preferred)

Emails

****@gmail.com (Confirmed)

****@google.com (Confirmed)

Personal Links

Homepage

Career & Education History

Research Scientist

DeepMind (google.com)

2019 – Present

Latent Logic

Latent Logic (latentlogic.com)

2017 – 2019

Postdoc

Imperial College London (ic.ac.uk)

2016 – 2017

PhD student

Imperial College London (ic.ac.uk)

2012 – 2016

MS student

Imperial College London (ic.ac.uk)

2010 – 2011

Advisors, Relations & Conflicts

No relations added

Expertise

Deep Reinforcement Learning

Present

Imitation Learning

Present

Meta Reinforcement Learning

Present

Publications

Self-Improving Foundation Models Without Human Supervision
Amrith Setlur, Katie Kang, Aviral Kumar, Feryal Behbahani, Roberta Raileanu, Rishabh Agarwal
- ICLR 2025 Workshop Proposals
- Readers: Everyone
Training Language Models to Self-Correct via Reinforcement Learning
Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, John D Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal Behbahani, Aleksandra Faust
- ICLR 2025 Oral
- Readers: Everyone
Many-Shot In-Context Learning
Rishabh Agarwal, Avi Singh, Lei M Zhang, Bernd Bohnet, Luis Rosias, Stephanie C.Y. Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, John D Co-Reyes, Eric Chu, Feryal Behbahani, Aleksandra Faust, Hugo Larochelle
- LCFM 2024
- Readers: Everyone
Many-Shot In-Context Learning
Rishabh Agarwal, Avi Singh, Lei M Zhang, Bernd Bohnet, Luis Rosias, Stephanie C.Y. Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, John D Co-Reyes, Eric Chu, Feryal Behbahani, Aleksandra Faust, Hugo Larochelle
- NeurIPS 2024 spotlight
- Readers: Everyone
Position: Open-Endedness is Essential for Artificial Superhuman Intelligence
Edward Hughes, Michael D Dennis, Jack Parker-Holder, Feryal Behbahani, Aditi Mavalankar, Yuge Shi, Tom Schaul, Tim Rocktäschel
- ICML 2024 Oral
- Readers: Everyone
Genie: Generative Interactive Environments
Jake Bruce, Michael D Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, Yusuf Aytar, Sarah Maria Elisabeth Bechtle, Feryal Behbahani, Stephanie C.Y. Chan, Nicolas Heess, Lucy Gonzalez, Simon Osindero, Sherjil Ozair, Scott Reed, Jingwei Zhang et al. (5 additional authors not shown)
- ICML 2024 Oral
- Readers: Everyone
Vision-Language Models as a Source of Rewards
Kate Baumli, Satinder Singh, Feryal Behbahani, Harris Chan, Gheorghe Comanici, Sebastian Flennerhag, Maxime Gazeau, Kristian Holsheimer, Dan Horgan, Michael Laskin, Clare Lyle, Volodymyr Mnih, Alexander Neitz, Fabio Pardo, Jack Parker-Holder, John Quan, Tim Rocktäschel, Himanshu Sahni, Tom Schaul, Yannick Schroecker et al. (4 additional authors not shown)
- ALOE 2023 Poster
- Readers: Everyone
Structured State Space Models for In-Context Reinforcement Learning
Chris Lu, Yannick Schroecker, Albert Gu, Emilio Parisotto, Jakob Nicolaus Foerster, Satinder Singh, Feryal Behbahani
- Frontiers4LCD
- Readers: Everyone
Structured State Space Models for In-Context Reinforcement Learning
Chris Lu, Yannick Schroecker, Albert Gu, Emilio Parisotto, Jakob Nicolaus Foerster, Satinder Singh, Feryal Behbahani
- NeurIPS 2023 poster
- Readers: Everyone
Human-Timescale Adaptation in an Open-Ended Task Space
Jakob Bauer, Kate Baumli, Feryal Behbahani, Avishkar Bhoopchand, Nathalie Bradley-Schmieg, Michael Chang, Natalie Clay, Adrian Collister, Vibhavari Dasagi, Lucy Gonzalez, Karol Gregor, Edward Hughes, Sheleem Kashem, Maria Loks-Thompson, Hannah Openshaw, Jack Parker-Holder, Shreya Pathak, Nicolas Perez-Nieves, Nemanja Rakicevic, Tim Rocktäschel et al. (7 additional authors not shown)
- ICML 2023 OralPoster
- Readers: Everyone

View all 20 publications

Co-Authors

View all 155 co-authors