Summary of Think While You Generate: Discrete Diffusion with Planned Denoising, by Sulin Liu et al.
Think While You Generate: Discrete Diffusion with Planned Denoising
by Sulin Liu, Juno Nam, Andrew Campbell, Hannes Stärk, Yilun Xu, Tommi Jaakkola, Rafael Gómez-Bombarelli
First submitted to arxiv on: 8 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces Discrete Diffusion with Planned Denoising (DDPD), a novel framework that separates the generation process into two models: a planner and a denoiser. The planner identifies corrupted positions in need of denoising, allowing for more efficient reconstruction during generation. DDPD outperforms traditional mask diffusion methods on language modeling benchmarks like text8, OpenWebText, and token-based generation on ImageNet 256×256. It also significantly reduces the performance gap between diffusion-based and autoregressive methods in terms of generative perplexity. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to make computers generate texts or images that are similar to real ones. The researchers created a new model called DDPD, which has two parts: one that plans what needs to be fixed and another that fixes it. This makes the process more efficient and gets better results than other models on certain tasks. It’s like having a personal assistant that helps you clean up mistakes as you go along. |
Keywords
» Artificial intelligence » Autoregressive » Diffusion » Mask » Perplexity » Token
