On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning

• URL: http://arxiv.org/abs/2506.00136v1
• Date: Fri, 30 May 2025 18:14:09 GMT
• Title: On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
• Authors: Magdalena Proszewska, Nikolay Malkin, N. Siddharth,
• Abstract summary: Diffusion autoencoders (DAs) use an input-dependent latent variable to capture representations alongside the diffusion process.<n>Better generative modelling is the primary goal of another class of diffusion models -- those that learn their forward (noising) process.
• Score: 14.707830064594056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. These representations, to varying extents, can be used for tasks such as downstream classification, controllable generation, and interpolation. However, the generative performance of DAs relies heavily on how well the latent variables can be modelled and subsequently sampled from. Better generative modelling is also the primary goal of another class of diffusion models -- those that learn their forward (noising) process. While effective at adjusting the noise process in an input-dependent manner, they must satisfy additional constraints derived from the terminal conditions of the diffusion process. Here, we draw a connection between these two classes of models and show that certain design decisions (latent variable choice, conditioning method, etc.) in the DA framework -- leading to a model we term DMZ -- allow us to obtain the best of both worlds: effective representations as evaluated on downstream tasks, including domain transfer, as well as more efficient modelling and generation with fewer denoising steps compared to standard DMs.

Related papers

• Diffusion models for multivariate subsurface generation and efficient probabilistic inversion [0.0]
  Diffusion models offer stable training and state-of-the-art performance for deep generative modeling tasks.<n>We introduce a likelihood approximation accounting for the noise-contamination that is inherent in diffusion modeling.<n>Our tests show significantly improved statistical robustness, enhanced sampling of the posterior probability density function.
  arXiv  Detail & Related papers  (2025-07-21T17:10:16Z)
• InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment [12.823734370183482]
  We introduce DDIM-InPO, an efficient method for direct preference alignment of diffusion models.<n>Our approach conceptualizes diffusion model as a single-step generative model, allowing us to fine-tune the outputs of specific latent variables selectively.<n> Experimental results indicate that our DDIM-InPO achieves state-of-the-art performance with just 400 steps of fine-tuning.
  arXiv  Detail & Related papers  (2025-03-24T08:58:49Z)
• DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers [86.5541501589166]
  DiffMoE is a batch-level global token pool that enables experts to access global token distributions during training.<n>It achieves state-of-the-art performance among diffusion models on ImageNet benchmark.<n>The effectiveness of our approach extends beyond class-conditional generation to more challenging tasks such as text-to-image generation.
  arXiv  Detail & Related papers  (2025-03-18T17:57:07Z)
• ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer [95.80384464922147]
  ACDiT is a blockwise Conditional Diffusion Transformer.<n>It offers a flexible between token-wise autoregression and full-sequence diffusion.<n>We show that ACDiT performs best among all autoregressive baselines on image and video generation tasks.
  arXiv  Detail & Related papers  (2024-12-10T18:13:20Z)
• Energy-Based Diffusion Language Models for Text Generation [126.23425882687195]
  Energy-based Diffusion Language Model (EDLM) is an energy-based model operating at the full sequence level for each diffusion step.<n>Our framework offers a 1.3$times$ sampling speedup over existing diffusion models.
  arXiv  Detail & Related papers  (2024-10-28T17:25:56Z)
• Neural Diffusion Models [2.1779479916071067]
  We present a generalization of conventional diffusion models that enables defining and learning time-dependent non-linear transformations of data. NDMs outperform conventional diffusion models in terms of likelihood and produce high-quality samples.
  arXiv  Detail & Related papers  (2023-10-12T13:54:55Z)
• DiffFlow: A Unified SDE Framework for Score-Based Diffusion Models and Generative Adversarial Networks [41.451880167535776]
  We propose a unified theoretic framework for explicit generative models (SDMs) and generative adversarial nets (GANs) Under our unified theoretic framework, we introduce several instantiations of the DiffFLow that provide new algorithms beyond GANs and SDMs with exact likelihood inference.
  arXiv  Detail & Related papers  (2023-07-05T10:00:53Z)
• Semi-Implicit Denoising Diffusion Models (SIDDMs) [50.30163684539586]
  Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps. We introduce a novel approach that tackles the problem by matching implicit and explicit factors. We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.
  arXiv  Detail & Related papers  (2023-06-21T18:49:22Z)
• Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models [77.83923746319498]
  We propose a framework called Diff-Instruct to instruct the training of arbitrary generative models. We show that Diff-Instruct results in state-of-the-art single-step diffusion-based models. Experiments on refining GAN models show that the Diff-Instruct can consistently improve the pre-trained generators of GAN models.
  arXiv  Detail & Related papers  (2023-05-29T04:22:57Z)
• Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models [58.357180353368896]
  We propose a conditional paradigm that benefits from the denoising diffusion probabilistic model (DDPM) to tackle the problem of realistic and diverse action-conditioned 3D skeleton-based motion generation. We are a pioneering attempt that uses DDPM to synthesize a variable number of motion sequences conditioned on a categorical action.
  arXiv  Detail & Related papers  (2023-01-10T13:15:42Z)
• f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation [56.04628143914542]
  Diffusion models (DMs) have recently emerged as SoTA tools for generative modeling in various domains. We propose f-DM, a generalized family of DMs which allows progressive signal transformation. We apply f-DM in image generation tasks with a range of functions, including down-sampling, blurring, and learned transformations.
  arXiv  Detail & Related papers  (2022-10-10T18:49:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.