5 papers
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…
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…
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…
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…
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…