Search papers, labs, and topics across Lattice.
DAVID Lab, University of Paris-Saclay, UVSQ, 78035 Versailles, France.
2
0
4
16
Forget reinforcement learning; the secret to collective intelligence may be as simple as agents independently minimizing their free energy.
By recasting attention as a cooperative game and a statistical physics system, NeuroGame Transformer captures higher-order token dependencies, outperforming standard pairwise attention mechanisms.
