10 papers
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
Yuchen Jiao, Na Li, Changxiao Cai +2
Diffusion-based methods have achieved remarkable empirical success in solving inverse problems. However, many existing posterior samplers either lack rigorous theoretical guarantee…
Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices
Changxiao Cai, Yuchen Jiao, Gen Li
Diffusion models are known to exploit unknown low-dimensional structure to accelerate sampling. However, existing convergence theory under low-dimensional data structure has largel…
Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
Jingda Wu, Changxiao Cai
Score-based diffusion models have demonstrated remarkable empirical success in learning high-dimensional distributions, particularly those exhibiting low-dimensional and multi-moda…
Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
Changxiao Cai, Gen Li
Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models for language modeling, allowing flexible generation order and parallel genera…
Adaptation to Intrinsic Dependence in Diffusion Language Models
Yunxiao Zhao, Changxiao Cai
Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive (AR) approaches, enabling parallel token generation beyond a rigid left-to-right…
Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
Gen Li, Changxiao Cai
Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregres…