AI RESEARCH
Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion
arXiv CS.LG
•
ArXi:2605.23346v1 Announce Type: new Discrete diffusion models have emerged as powerful frameworks for generating structured categorical data. However, efficiently sampling from reward-tilted distributions remains a fundamental challenge. While Twisted Sequential Monte Carlo (SMC) offers asymptotic exactness for this task, estimating the optimal twist function in discrete state spaces necessitates costly Monte Carlo approximations, resulting a severe computational bottleneck at inference. To overcome this limitation, we