Hugging Face Trending Papers
Unlocking Spatial Grounding in Flow-Matching Models via SNR Tuning
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Oct 22
Unlocking Spatial Grounding in Flow-Matching Models via SNR Tuning
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.
arXiv Computer Vision
1d ago
GeoCore-9B: Towards Geo-Aware Generative Foundation Models in Earth Observation
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 AI
Jun 16
Efficient Flow Matching using Latent Variables
arXiv:2505. 04486v4 Announce Type: replace-cross Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models.
arXiv AI
Aug 3
MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation
arXiv:2607. 29180v1 Announce Type: cross Abstract: Text-to-motion generation must produce motions that are semantically correct, temporally coherent, and physically plausible.
Hugging Face Trending Papers
Jul 7
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image 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.
Hugging Face Trending Papers
Jul 14
DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
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.