Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
2
0
3
Machine-learned densities of states, despite losing most band gaps, still effectively rank high-performance thermoelectrics within the top 1% of candidates, certifying 80 new computational discoveries.
PINNs get a wavelet makeover, adaptively focusing on high-magnitude source regions and leaving vanilla methods in the dust on PDEs with extreme loss imbalances.