3 papers
cs.LG2026
On the -Free Inference Complexity of Absorbing Discrete Diffusion
Xunpeng Huang, Yingyu Lin, Nishant Jain +4
Absorbing discrete diffusion has emerged as a dominant framework for discrete data generation. However, a significant disparity remains between its empirical success and theoretica…
stat.ML2025
A Sharp KL-Convergence Analysis for Diffusion Models under Minimal Assumptions
Nishant Jain, Tong Zhang
Diffusion-based generative models have emerged as highly effective methods for synthesizing high-quality samples. Recent works have focused on analyzing the convergence of their ge…
cs.LG2025
Multi-Step Consistency Models: Fast Generation with Theoretical Guarantees
Nishant Jain, Xunpeng Huang, Yian Ma +1
Consistency models have recently emerged as a compelling alternative to traditional SDE-based diffusion models. They offer a significant acceleration in generation by producing hig…