Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
4
Muon's finite-step orthogonalization provably guarantees reaching any target training loss for wide networks, resolving a key theoretical gap.
Uniform sampling fails to adequately cover the vulnerability landscape of neural operators, as optimal training data is architecture-dependent, necessitating targeted data generation strategies.
Forget retraining monolithic models: SCNO unlocks zero-forgetting modular expansion for PDE solvers by composing spiking neural operator blocks, outperforming traditional methods with fewer parameters.
Achieve real-time, accurate virtual sensing on edge devices with VIRSO, a graph neural operator that slashes energy consumption by 20x compared to previous methods.
