The paper shows that the signal‑to‑noise ratio (SNR) distribution is key to achieving fine‑grained spatial control in flow‑matching generative models. By training on high‑noise regimes rather than a centered SNR distribution, the authors raise layout adherence from 25.9 % to 80.8 % on a synthetic benchmark, approaching the 83.6 % ceiling of the underlying variational autoencoder. These insights also improve real‑world layout accuracy on COCO, boosting average precision from 1.0 % to 57.3 % without changing the model architecture.
Despite the success of foundation models in image synthesis, achieving fine-grained spatial control remains a significant challenge, typically requiring auxiliary structural adapters or complex infere...
arXiv:2608.01896v2 Announce Type: replace Abstract: Existing generative models for earth observation (EO) predominantly rely on fine-tuning natural image priors, which limits their scalability and in...
arXiv:2505. 04486v4 Announce Type: replace-cross Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models.
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets.
arXiv:2605.12957v2 Announce Type: replace Abstract: Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of do...
arXiv:2609.35734v2 Announce Type: replace Abstract: Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, whi...
arXiv:2607. 16409v1 Announce Type: cross Abstract: Unified Multimodal Large Language Models (MLLMs) offer a promising paradigm for unifying visual understanding and generation, yet they still struggle to follow complex spatial instructions and logical constraints in controllable image generation.
arXiv:2607. 29180v1 Announce Type: cross Abstract: Text-to-motion generation must produce motions that are semantically correct, temporally coherent, and physically plausible.
The paper investigates how visual representations contribute to pixel diffusion transformers and finds that higher representation quality does not always improve generative performance, and that separating architecture into specialized decoders mainly redistributes modeling rather than enhancing generative suitability. Based on these findings, the authors propose Representation Guidance (RG), a method that compacts generation-relevant information into a low-dimensional bottleneck and explicitly uses it to steer decoder generation. RG achieves state‑of‑the‑art results on ImageNet 256×256 with fewer parameters, scales efficiently, and extends to text‑to‑image tasks with strong benchmark performance.
arXiv:2606. 25128v1 Announce Type: cross Abstract: Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs.
arXiv:2609.35763v3 Announce Type: replace Abstract: Distributional training provides collective supervision for one-step visual generation by matching real and generated features in frozen representa...
Despite remarkable progress in text-guided image editing, generative models frequently fail to preserve visual object consistency, defined as the preservation of a subject's key attributes throughout the editing process. We address this limitation through three contributions.