# Masked Generative Modeling with Enhanced Sampling Scheme

arXiv: https://arxiv.org/abs/2309.07945 · HTML: https://mlsanity.com/paper/2309.07945/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 14 Sep 2023.

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Generative Moment Matching Networks](https://mlsanity.com/paper/1502.02761/) (2015)
- [Improved Masked Image Generation with Token-Critic](https://mlsanity.com/paper/2209.04439/) (2022)
- [Vector Quantized Time Series Generation with a Bidirectional Prior Model](https://mlsanity.com/paper/2303.04743/) (2023)
- [Conditional GAN for timeseries generation](https://mlsanity.com/paper/2006.16477/) (2020)
- [Why Are Conditional Generative Models Better Than Unconditional Ones?](https://mlsanity.com/paper/2212.00362/) (2022)
- [TSGBench: Time Series Generation Benchmark](https://mlsanity.com/paper/2309.03755/) (2023)
- [TTS-CGAN: A Transformer Time-Series Conditional GAN for Biosignal Data Augmentation](https://mlsanity.com/paper/2206.13676/) (2022)

## Built on by (most cited first, 3 of 3)

- [Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling](https://mlsanity.com/paper/2311.12550/) (2023)
- [Latent Diffusion Model for Conditional Reservoir Facies Generation](https://mlsanity.com/paper/2311.01968/) (2023)
- [BIGFix: Bidirectional Image Generation with Token Fixing](https://mlsanity.com/paper/2510.12231/) (2025)

## Abstract (arXiv)

This paper presents a novel sampling scheme for masked non-autoregressive generative modeling. We identify the limitations of TimeVQVAE, MaskGIT, and Token-Critic in their sampling processes, and propose Enhanced Sampling Scheme (ESS) to overcome these limitations. ESS explicitly ensures both sample diversity and fidelity, and consists of three stages: Naive Iterative Decoding, Critical Reverse Sampling, and Critical Resampling. ESS starts by sampling a token set using the naive iterative decoding as proposed in MaskGIT, ensuring sample diversity. Then, the token set undergoes the critical reverse sampling, masking tokens leading to unrealistic samples. After that, critical resampling reconstructs masked tokens until the final sampling step is reached to ensure high fidelity. Critical resampling uses confidence scores obtained from a self-Token-Critic to better measure the realism of sampled tokens, while critical reverse sampling uses the structure of the quantized latent vector space to discover unrealistic sample paths. We demonstrate significant performance gains of ESS in both unconditional sampling and class-conditional sampling using all the 128 datasets in the UCR Time Series archive.