2 papers
cs.LG2026
A Goal-Set Characterization of Task Composition in the Boolean Task Algebra
Eduardo Terrés-Caballero, Herke van Hoof
The Boolean Task Algebra (BTA) provides a principled framework for zero-shot task composition in reinforcement learning by equipping goal-reaching tasks with Boolean operations. We…
cs.LG2025
Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization
Odysseas Boufalis, Jorge Carrasco-Pollo, Joshua Rosenthal +2
Neural network parameterizations exhibit inherent symmetries that yield multiple equivalent minima within the loss landscape. Scale Graph Metanetworks (ScaleGMNs) explicitly levera…