Search papers, labs, and topics across Lattice.
Affiliation:, Texas A&M University, Carnegie Mellon University
2
2
5
6
A 5-step sampling schedule can deliver nearly the same quality as a 50-step one, slashing inference costs by 90%.
By pausing to "think" with latent diffusion, STAR-LDM achieves superior language understanding, narrative coherence, and controllable generation compared to standard autoregressive models of similar size.
