6 papers
From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
Yuchen Liang, Ness Shroff, Yingbin Liang
Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to g…
Sharp Convergence Rates for Masked Diffusion Models
Yuchen Liang, Zhiheng Tan, Ness Shroff +1
Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, with masked (absorbing-rate) variants emerging as competitive alternatives…
Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees
Yuchen Liang, Yingbin Liang, Lifeng Lai +1
Discrete diffusion models have recently gained significant prominence in applications involving natural language and graph data. A key factor influencing their effectiveness is the…
Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
Yuchen Liang, Renxiang Huang, Lifeng Lai +2
Discrete state space diffusion models have shown significant advantages in applications involving discrete data, such as text and image generation. It has also been observed that t…
Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
Yuchen Liang, Peizhong Ju, Yingbin Liang +1
The denoising diffusion model has recently emerged as a powerful generative technique, capable of transforming noise into meaningful data. While theoretical convergence guarantees…
Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach
Yuchen Liang, Peizhong Ju, Yingbin Liang +1
Accelerated diffusion models hold the potential to significantly enhance the efficiency of standard diffusion processes. Theoretically, these models have been shown to achieve fast…