2 papers
cs.RO2024
LIMT: Language-Informed Multi-Task Visual World Models
Elie Aljalbout, Nikolaos Sotirakis, Patrick van der Smagt +2
Most recent successes in robot reinforcement learning involve learning a specialized single-task agent. However, robots capable of performing multiple tasks can be much more valuab…
cs.LG2024
DomainLab: A modular Python package for domain generalization in deep learning
Xudong Sun, Carla Feistner, Alexej Gossmann +10
Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniq…