Cansu Sancaktar

17 papers A* 5Journal 10Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula.
CoRR
Cansu Sancaktar, David W. Zhang, Gabriel Synnaeve, Taco Cohen
2026 J jnl
GASP: Guided Asymmetric Self-Play For Coding LLMs.
CoRR
Swadesh Jana, Cansu Sancaktar, Tomás Danis, Georg Martius, Antonio Orvieto, Pavel Kolev
2025 J jnl
Hybrid Training for Vision-Language-Action Models.
CoRR
Pietro Mazzaglia, Cansu Sancaktar, Markus Peschl, Daniel Dijkman
2025 J jnl
Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies.
CoRR
Jiaqi Chen, Ji Shi, Cansu Sancaktar, Jonas Frey, Georg Martius
2025 A* conf
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models.
ICML
Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk, Pavel Kolev, Georg Martius
2025 J jnl
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models.
CoRR
Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk, Pavel Kolev, Georg Martius
2024 A* conf
Modelling Microbial Communities with Graph Neural Networks.
ICML
Albane Ruaud, Cansu Sancaktar, Marco Bagatella, Christoph Ratzke, Georg Martius
2023 A* conf
Optimistic Active Exploration of Dynamical Systems.
NeurIPS
Bhavya Sukhija, Lenart Treven, Cansu Sancaktar, Sebastian Blaes, Stelian Coros, Andreas Krause
2023 J jnl
Optimistic Active Exploration of Dynamical Systems.
CoRR
Bhavya Sukhija, Lenart Treven, Cansu Sancaktar, Sebastian Blaes, Stelian Coros, Andreas Krause
2023 J jnl
Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World.
CoRR
Nico Gürtler, Felix Widmaier, Cansu Sancaktar, Sebastian Blaes, Pavel Kolev, Stefan Bauer, Manuel Wüthrich, Markus Wulfmeier, Martin A. Riedmiller, Arthur Allshire, Qiang Wang, Robert McCarthy, Hangyeol Kim, Jongchan Baek, Wookyong Kwon, Shanliang Qian, Yasunori Toshimitsu, Mike Yan Michelis, Amirhossein Kazemipour, Arman Raayatsanati, Hehui Zheng, Barnabas Gavin Cangan, Bernhard Schölkopf, Georg Martius
2023 A* conf
Regularity as Intrinsic Reward for Free Play.
NeurIPS
Cansu Sancaktar, Justus H. Piater, Georg Martius
2023 J jnl
Regularity as Intrinsic Reward for Free Play.
CoRR
Cansu Sancaktar, Justus H. Piater, Georg Martius
2022 A* conf
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation.
NeurIPS
Cansu Sancaktar, Sebastian Blaes, Georg Martius
2022 J jnl
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation.
CoRR
Cansu Sancaktar, Sebastian Blaes, Georg Martius
2021 — conf
Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World.
NeurIPS (Competition and Demos)
Nico Gürtler, Felix Widmaier, Cansu Sancaktar, Sebastian Blaes, Pavel Kolev, Stefan Bauer, Manuel Wüthrich, Markus Wulfmeier, Martin A. Riedmiller, Arthur Allshire, Qiang Wang, Robert McCarthy, Hangyeol Kim, Jongchan Baek, Wookyong Kwon, Shanliang Qian, Yasunori Toshimitsu, Mike Yan Michelis, Amirhossein Kazemipour, Arman Raayatsanati, Hehui Zheng, Barnabas Gavin Cangan, Bernhard Schölkopf, Georg Martius
2020 — conf
End-to-End Pixel-Based Deep Active Inference for Body Perception and Action.
ICDL-EPIROB
Cansu Sancaktar, Marcel A. J. van Gerven, Pablo Lanillos
2020 J jnl
End-to-End Pixel-Based Deep Active Inference for Body Perception and Action.
CoRR
Cansu Sancaktar, Pablo Lanillos