Search papers, labs, and topics across Lattice.
Affiliation:
4
0
5
22
Operators can be learned more efficiently with kernel methods that outperform deep learning models while maintaining high predictive accuracy.
Multi-task operator learning with shared representations doesn't cost you extra – it scales just as well as learning each operator individually.
Achieve explicit generalization guarantees for Multiple Neural Operator (MNO) networks, revealing how performance scales with the number of sampled operators.
By fusing orthogonalized momentum with adaptive noise scaling, NAMO and NAMO-D offer a surprisingly simple recipe for faster and more stable LLM training compared to AdamW and Muon.
