collaborators

5 papers

cs.RO2026

Hybrid Training for Vision-Language-Action Models

Pietro Mazzaglia, Cansu Sancaktar, Markus Peschl +1

Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful recipe for solving complex language ta…

cs.LG2026

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

Cansu Sancaktar, David Zhang, Gabriel Synnaeve +1

Reinforcement learning (RL) has emerged as a powerful paradigm for improving large language models beyond supervised fine-tuning, yet sustaining performance gains at scale remains…

cs.LG2026

GASP: Guided Asymmetric Self-Play For Coding LLMs

Swadesh Jana, Cansu Sancaktar, Tomáš Daniš +3

Asymmetric self-play has emerged as a promising paradigm for post-training large language models, where a teacher continually generates questions for a student to solve at the edge…

cs.LG2025

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

Jiaqi Chen, Ji Shi, Cansu Sancaktar +2

Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting…

cs.AI2025

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

Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk +2

Exploration is a cornerstone of reinforcement learning (RL). Intrinsic motivation attempts to decouple exploration from external, task-based rewards. However, established approache…