B-DENSE: Branching For Dense Ensemble Network Supervision Efficiency

ArXi:2602.15971v2 Announce Type: replace-cross Inspired by non-equilibrium thermodynamics, diffusion models have achieved state-of-the-art performance in generative modeling. However, their iterative sampling nature results in high inference latency. While recent distillation techniques accelerate sampling, they discard intermediate trajectory steps. This sparse supervision leads to a loss of structural information and