Cansu Sancaktar

According to our database, Cansu Sancaktar authored at least 12 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula.

Cansu Sancaktar, David W. Zhang, Gabriel Synnaeve, Taco Cohen

CoRR, March, 2026

GASP: Guided Asymmetric Self-Play For Coding LLMs.

Swadesh Jana, Cansu Sancaktar, Tomás Danis, Georg Martius, Antonio Orvieto, Pavel Kolev

CoRR, March, 2026

2025

Hybrid Training for Vision-Language-Action Models.

Pietro Mazzaglia, Cansu Sancaktar, Markus Peschl, Daniel Dijkman

CoRR, October, 2025

Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies.

Jiaqi Chen, Ji Shi, Cansu Sancaktar, Jonas Frey, Georg Martius

CoRR, September, 2025

SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models.

Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk, Pavel Kolev, Georg Martius

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Modelling Microbial Communities with Graph Neural Networks.

Albane Ruaud, Cansu Sancaktar, Marco Bagatella, Christoph Ratzke, Georg Martius

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Optimistic Active Exploration of Dynamical Systems.

Bhavya Sukhija, Lenart Treven, Cansu Sancaktar, Sebastian Blaes, Stelian Coros, Andreas Krause

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Regularity as Intrinsic Reward for Free Play.

Cansu Sancaktar, Justus H. Piater, Georg Martius

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation.

Cansu Sancaktar, Sebastian Blaes, Georg Martius

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World.

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

Proceedings of the NeurIPS 2022 Competition Track, 2021

2020

End-to-End Pixel-Based Deep Active Inference for Body Perception and Action.

Cansu Sancaktar, Pablo Lanillos

CoRR, 2020

End-to-End Pixel-Based Deep Active Inference for Body Perception and Action.

Cansu Sancaktar, Marcel A. J. van Gerven, Pablo Lanillos

Proceedings of the Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics, 2020