Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees
Authors: Yuchen Liang, Yingbin Liang, Lifeng LAI, Ness Shroff
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we provide some numerical simulations to validate our theoretical results. The target distribution is a synthetic autoregressive model with given coefficients. Here d = 2. We use Euler method to obtain 2000000 samples to estimate the KL divergence. |
| Researcher Affiliation | Academia | Yuchen Liang , Yingbin Liang , Lifeng Lai , Ness Shroff The Ohio State University University of California, Davis |
| Pseudocode | Yes | Algorithm 1: Euler method (e.g., in [10, 22]) Algorithm 2: Tweedie τ-leaping [10] Algorithm 3: Truncated τ-leaping (used in Appendix H) |
| Open Source Code | No | The paper does not contain any explicit statements about the release of source code, nor does it provide any links to code repositories. The NeurIPS Paper Checklist for 'Experimental result reproducibility' and 'Open access to data and code' states: 'The paper does not contain experimental results.' |
| Open Datasets | No | The target distribution is a synthetic autoregressive model with given coefficients. |
| Dataset Splits | No | The paper uses synthetic data and performs numerical simulations, but does not describe any training/test/validation splits for a real dataset. It mentions obtaining '2000000 samples to estimate the KL divergence' and '30000 samples to estimate the TV distance', which refers to sample sizes for simulation, not dataset splits. |
| Hardware Specification | No | The NeurIPS Paper Checklist for 'Experiments compute resources' states: 'The paper does not contain experimental results.' Therefore, no hardware specifications are provided. |
| Software Dependencies | No | The NeurIPS Paper Checklist for 'Experiments compute resources' states: 'The paper does not contain experimental results.' Therefore, no software dependencies with version numbers are provided. |
| Experiment Setup | Yes | In this section, we provide some numerical simulations to validate our theoretical results. The target distribution is a synthetic autoregressive model with given coefficients. Here d = 2. We use Euler method to obtain 2000000 samples to estimate the KL divergence. ... Figure 2: Estimated total variation distance between the target and sampling distribution of different sampling methods. Here d = 3 and S = 8. We use 30000 samples to estimate the TV distance. |