arXiv:2512. 20963v3 Announce Type: replace Abstract: Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training objective.
The paper introduces Latent Nonlinear Denoising Score Matching (LNDSM), a method that integrates nonlinear, structure-informed latent diffusions with a variational autoencoder framework. LNDSM designs the forward diffusion to admit a chosen reference distribution, such as a Gaussian mixture, and derives a computable approximation to a cross‑entropy upper bound using Euler‑Maruyama discretization. Experiments on benchmark image datasets show that LNDSM improves sample quality, mode balance, and training efficiency compared to conventional latent score‑based generative models.
arXiv:2501. 09876v3 Announce Type: replace-cross Abstract: Generative modeling aims to generate new data samples that resemble a given dataset.
arXiv:2602.10216v2 Announce Type: replace Abstract: A single text prompt passed to a diffusion model yields a wide range of visual outputs determined solely by a stochastic process, leaving users wit...
arXiv:2609.37533v1 Announce Type: new Abstract: Masked diffusion models (MDMs) generate sequences by progressively unmasking several tokens per denoising step, but their reverse process is typically...
The article surveys how diffusion and flow-based generative models learn rich visual representations and how these representations can be used to improve generation and other perception tasks. It introduces a three-tier framework that categorizes work into improving generative quality via representation learning, extracting representations for perception, and developing unified applications. The survey covers downstream tasks such as image classification, dense prediction, instance-level perception, and annotation-scarce scenarios, offering a taxonomy and highlighting future research directions.
Diffusion models and flow-based models have recently become the dominant paradigms in generative modeling, largely due to their ability to learn rich, multi-level visual representations through large-...
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:2411.05005v2 Announce Type: replace-cross Abstract: Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, m...
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.
The paper proposes a self‑supervised representation learning method that serves as a tokenizer for generative models. It supervises a representation loss by factorizing pointwise mutual information, estimated through differences between conditional predictions of a learned generative model. The authors demonstrate that this approach avoids dimensional collapse and feature suppression seen in methods like DINO and LeJEPA, scales predictably with compute, and achieves compute‑optimal performance over direct diffusion for pixel‑space generation, with strong scaling laws on ImageNet and GPIC.
The paper introduces SAEParate, a sparse autoencoder approach that explicitly separates overlapping concepts in the latent space of text-to-image diffusion models. It employs concept-aware contrastive learning and cross-attention-guided spatial aggregation to focus on concept-relevant regions, while a nonlinear encoder transformation enhances expressive capacity. Experiments on UnlearnCanvas show state‑of‑the‑art performance, especially in challenging joint style‑object unlearning scenarios where prior methods struggle with interference between concepts.