Search papers, labs, and topics across Lattice.
Texas A&M University
2
0
4
Transforming autoregressive models into diffusion models can be achieved with up to 7,000x fewer training tokens, revolutionizing the efficiency of model training.
Skip the computationally expensive propagation of all occupied states in real-time TDDFT: a new equivariant graph transformer, OrbEvo, learns to evolve electronic wavefunctions directly.
