Search papers, labs, and topics across Lattice.
4
0
6
0
Embodied agents improve on complex tasks by recombining learned skills, but their ability to extract value from additional experience saturates, failing to scale with learning samples.
High-norm outlier tokens, often preserved by existing methods, are actually redundant and can be pruned without sacrificing performance鈥擲inkPruner proves it with an 89% token reduction while retaining over 96% of model effectiveness.
The data pyramid framework reveals how the interplay of diverse data sources can unlock new capabilities in embodied agents, highlighting critical gaps in current methodologies.
