Search papers, labs, and topics across Lattice.
2
3
4
17
Parameter-efficient adaptation methods can match full fine-tuning gains for tabular foundation models, while selective aggregation offers a clear path to improved predictions over ensemble averaging.
Ditch reward models: Nash Mirror Prox achieves fast, stable convergence to a Nash equilibrium directly from human preferences, sidestepping the limitations of traditional RLHF.
