Serkan Cabi

Google DeepMind (United Kingdom) — United Kingdom

Computer Science · Physical Sciences

13h-index2.2kcitations28works1.62yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(10), Robot Manipulation and Learning(9), Topic Modeling(6), Human Pose and Action Recognition(5), Domain Adaptation and Few-Shot Learning(5)

Publications28 total

Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
arXiv (Cornell University)·2025Open Access
Improving cosmological reach of a gravitational wave observatory using Deep Loop Shaping
Science·2025· 3 citedOpen Access
Gemini Robotics: Bringing AI into the Physical World
arXiv (Cornell University)·2025· 4 citedOpen Access
Vision-Language Model Dialog Games for Self-Improvement
arXiv (Cornell University)·2025Open Access
GATS: Gather-Attend-Scatter
arXiv (Cornell University)·2024· 1 citedOpen Access
Vision-Language Models as Success Detectors
arXiv (Cornell University)·2023· 11 citedOpen Access
Flamingo: a Visual Language Model for Few-Shot Learning
arXiv (Cornell University)·2022· 1.2k citedOpen Access
Single-molecule mechanical fingerprinting with DNA nanoswitch calipers
Nature Nanotechnology·2021· 49 citedOpen Access
Multimodal Few-Shot Learning with Frozen Language Models
arXiv (Cornell University)·2021· 86 citedOpen Access
Semi-supervised reward learning for offline reinforcement learning
arXiv (Cornell University)·2020· 7 citedOpen Access
Scaling data-driven robotics with reward sketching and batch reinforcement learning
2020· 59 cited
Acme: A Research Framework for Distributed Reinforcement Learning
arXiv (Cornell University)·2020· 73 citedOpen Access
Task-Relevant Adversarial Imitation Learning
arXiv (Cornell University)·2019· 22 citedOpen Access
A Framework for Data-Driven Robotics
arXiv (Cornell University)·2019· 11 citedOpen Access
Scaling data-driven robotics with reward sketching and batch reinforcement learning
arXiv (Cornell University)·2019· 45 citedOpen Access
Task-Relevant Adversarial Imitation Learning
arXiv (Cornell University)·2019· 2 citedOpen Access
One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
arXiv (Cornell University)·2018· 5 citedOpen Access
One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
arXiv (Cornell University)·2018· 17 citedOpen Access
Reinforcement and Imitation Learning for Diverse Visuomotor Skills
2018· 213 citedOpen Access
Learning Awareness Models
arXiv (Cornell University)·2018· 13 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Nando de Freitas(16), Sergio Gómez Colmenarejo(13), Misha Denil(11), Scott Reed(8), Ziyu Wang(7), Konrad Żołna(7), David Budden(7), Yusuf Aytar(6), Ksenia Konyushkova(6), Alexander Novikov(5), Tom Erez(4), Nicolas Heess(4), Jean-Baptiste Alayrac(3), Oriol Vinyals(3), Gabriel Barth-Maron(3), Abbas Abdolmaleki(3), Tom Le Paine(3), Rae Jeong(3), Mel Vecerík(3), Oleg Sushkov(3)