AnyGoal tests world-model generalization beyond expert rollouts
Current models fail when familiar state and action factors are recombined into underrepresented combinations.
5 stories, newest first · one card per story
Current models fail when familiar state and action factors are recombined into underrepresented combinations.
EmbodiedCLBench measures whether embodied agents can recombine basic skills for harder unseen tasks.
Mu-DisCoCat uses variational quantum circuits to improve compositional generalization on noisy near-term quantum hardware.
AE-VLA lifts dual-arm generalization to 21.53% in simulation and 39% on SO101 robots.
Researchers show lexical-versus-structural compositional generalization gaps in Transformers stem from type diversity imbalance in datasets, not architectural limits.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views