Computer Science - Robotics
Subcategories
Papers
Diffusion Beats Autoregressive in Data-Constrained Settings
Mihir Prabhudesai, et al. • (2025) • DOI:
10.48550/arXiv.2507.15857
Autoregressive (AR) models have long dominated the landscape of large language models, driving progress across a wide range of tasks. Recently, diffusion-based language models have emerged as a promis...
General agents need world models
Jonathan Richens, et al. •
• (2025) • DOI:
10.48550/arXiv.2506.01622
Are world models a necessary ingredient for flexible, goal-directed behaviour, or is model-free learning sufficient? We provide a formal answer to this question, showing that any agent capable of gene...
Illuminating search spaces by mapping elites
Jean-Baptiste Mouret, Jeff Clune •
• (2015) • DOI:
10.48550/arXiv.1504.04909
Many fields use search algorithms, which automatically explore a search space to find high-performing solutions: chemists search through the space of molecules to discover new drugs; engineers search ...