====== Diffusion Models ======

===== Overviews =====
  * [[https://arxiv.org/pdf/2209.00796|Yang et al 2022 - Diffusion Models: A Comprehensive Survey of Methods and Applications]]
  * **Tutorials**
    * [[https://arxiv.org/pdf/2406.08929|Nakkiran et al 2024 - Step-by-Step Diffusion: An Elementary Tutorial]]
    * [[https://arxiv.org/pdf/2301.11108|McAllester 2023 - On the Mathematics of Diffusion Models]]
  * **In NLP**
    * [[https://arxiv.org/pdf/2303.07576|Zhu & Zhao 2023 - Diffusion Models in NLP: A Survey]]
    * [[https://arxiv.org/pdf/2305.14671|Zou et al 2023 - Survey of Diffusion Models in Natural Language Processing]]


===== Key Papers =====
  * [[https://arxiv.org/pdf/2006.11239|Ho et al 2020 - Denoising Diffusion Probabilistic Models]] The one that started it all (for image generation)

===== Image and Video Generation =====
  * [[https://arxiv.org/pdf/2104.07636|Saharia et al 2021 - Image Super-Resolution via Iterative Refinement]]
  * Stable Diffusion: [[https://arxiv.org/pdf/2112.10752|Rombach et al 2021 - High-Resolution Image Synthesis with Latent Diffusion Models]]
  * [[https://arxiv.org/pdf/2311.15127|Blattmann et al 2023 - Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets]]

===== Diffusion Models in NLP =====
  * [[https://arxiv.org/pdf/2205.14217|Li et al 2022 - Diffusion-LM Improves Controllable Text Generation]]
  * [[https://arxiv.org/pdf/2302.05737|Zheng et al 2023 - Reparameterized Discrete Diffusion Model for Text Generation]]
  * [[https://arxiv.org/pdf/2402.07754|Ye et al 2024 - Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models]]
  * **LLaDA: [[https://arxiv.org/pdf/2502.09992|Nie et al 2025 - Large Language Diffusion Models]]**
  * [[https://arxiv.org/pdf/2503.09573|Arriola et al 2025 - Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models]]
  * [[https://arxiv.org/pdf/2505.22165|Li et al 2025 - Unifying Continuous and Discrete Text Diffusion with Non-simultaneous Diffusion Processes]]
  * [[https://arxiv.org/pdf/2505.22618|Wu et al 2025 - Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding]] Nvidia paper

===== Related Pages =====
  * [[Image Generation]]