17 citations · 39 across the 17 of their papers we have counts for
10 papers · 1 filter
Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure
Jingda Wu, Changxiao Cai
Masked diffusion models (MDMs) generate discrete data by iteratively unmasking multiple tokens in parallel using a learned mask predictor. Their output carries two errors: parallel…
Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds
Yunxiao Zhao, Changxiao Cai
Speculative decoding accelerates large language model inference by using a low-cost draft model to propose tokens that the full-size target model verifies in parallel. Parallel and…
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…
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…
Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
Gen Li, Changxiao Cai, Yuting Wei
Diffusion models are distinguished by their exceptional generative performance, particularly in producing high-quality samples through iterative denoising. While current theory sug…
Minimax Optimality of the Probability Flow ODE for Diffusion Models
Changxiao Cai, Gen Li
Score-based diffusion models have become a foundational paradigm for modern generative modeling, demonstrating exceptional capability in generating samples from complex high-dimens…
Provable Acceleration for Diffusion Models under Minimal Assumptions
Gen Li, Changxiao Cai
Score-based diffusion models, while achieving minimax optimality for sampling, are often hampered by slow sampling speeds due to the high computational burden of score function eva…
Nonconvex Low-Rank Tensor Completion from Noisy Data
Changxiao Cai, Gen Li, H. Vincent Poor +1
We study a noisy tensor completion problem of broad practical interest, namely, the reconstruction of a low-rank tensor from highly incomplete and randomly corrupted observations o…