AI RESEARCH
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
arXiv CS.LG
•
ArXi:2503.22886v2 Announce Type: replace Recent advancements in imitation learning have led to transformer-based behavior foundation models (BFMs) that enable multi-modal, human-like control for humanoid agents. While excelling at zero-shot generation of robust behaviors, BFMs often require meticulous prompt engineering for specific tasks, potentially yielding suboptimal results. We