arXiv:2604. 02751v2 Announce Type: replace Abstract: Diffusion models often degrade in latent spaces, yet the formal causes remain poorly understood.
arXiv:2608. 04827v1 Announce Type: cross Abstract: We introduce the Intrinsic Hybrid Latent Diffusion Model (ILDM), a generative framework that integrates probabilistic dimensionality reduction with geometry-aware diffusion on unknown manifolds.
arXiv:2608.23916v1 Announce Type: new Abstract: Denoising score matching trains diffusion models by regressing onto a conditional score, although generation ultimately requires the marginal score. Th...
arXiv:2501. 09876v3 Announce Type: replace-cross Abstract: Generative modeling aims to generate new data samples that resemble a given dataset.
We introduce the Intrinsic Hybrid Latent Diffusion Model (ILDM), a generative framework that integrates probabilistic dimensionality reduction with geometry-aware diffusion on unknown manifolds. While diffusion models (DMs) have achieved state-of-the-art results in high-dimensional data synthesis, they rely on large training datasets and ignore intrinsic geometric structure.
arXiv:2409. 18804v3 Announce Type: replace-cross Abstract: Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond.
Latent diffusion models achieve strong generative performance by operating in a compressed latent space produced by a variational autoencoder (VAE). However, it remains unclear whether all latent channels contribute equally to the diffusion process, or whether significant redundancy exists.
arXiv:2506. 00849v2 Announce Type: replace Abstract: Despite the empirical success of Diffusion Models (DMs) and Variational Autoencoders (VAEs), their generalization performance remains theoretically underexplored, especially lacking a full consideration of the shared encoder-generator structure.
The paper investigates how fine‑tuning pretrained visual encoders for faithful image reconstruction affects diffusion models that operate in the resulting latent space. It finds that such fine‑tuning reduces the effective dimensionality of the latent representation, causing standard velocity‑prediction flow‑matching to fit noise outside the low‑dimensional signal manifold and making optimization inefficient. Consequently, the authors propose using a clean‑data ($oldsymbol{x}_{0}$) parameterization, which focuses learning on the signal manifold and consistently improves text‑to‑image generation across multiple strong‑reconstruction encoders.
arXiv:2606. 16610v1 Announce Type: cross Abstract: Diffusion Flow Matching (DFM) has recently emerged as a versatile framework for generative modeling, yet its theoretical convergence properties remain only partially understood.
This article reviews recent diffusion‑based methods for generative lossy image compression, highlighting how these techniques encode a source into an embedding and use a diffusion model to iteratively refine the reconstruction during decoding. It discusses the role of auxiliary entropy models for transmitting the embedding, explores the use of diffusion models for information transmission via channel simulation, and frames the discussion within rate‑distortion‑perception theory, common randomness, and inverse‑problem connections. The review also identifies open challenges in the field.
arXiv:2607. 10067v1 Announce Type: new Abstract: While autoregressive models optimize the exact data likelihood via the chain rule, diffusion models are typically trained with denoising objectives.
arXiv:2606. 28228v1 Announce Type: new Abstract: Causal representation learning for time series has developed strong identifiability results in discrete-time latent causal models, but identifiability in continuous-time latent stochastic differential equation (SDE) models remains largely open.