← Back to all news
Hugging Face Trending Papers

Efficient Covariance-Aware Vicinal Latent Diffusion for Continuous Conditional Image Generation

Read the original on Hugging Face Trending Papers →

Efficient Covariance-Aware Vicinal Latent Diffusion (CAViLD) is a latent diffusion framework designed for continuous conditional image generation. It builds a purified, condition-aware latent space using density-adaptive vicinal learning, auxiliary semantic regularization, and NIQE-guided negative data augmentation. CAViLD incorporates an EMA teacher to internalize conditional guidance, enabling single-branch inference, and employs covariance-aware progressive distillation to reduce sampling steps to four NFEs, achieving a balance between fidelity, condition consistency, and efficiency on datasets such as RC-49, UTKFace, and Steering Angle.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

Related stories

arXiv Machine Learning
Jun 8

Drifting Models for Surrogate Flow Modeling

arXiv:2606. 07481v1 Announce Type: new Abstract: While Computational Fluid Dynamics (CFD) provides high-fidelity flow fields for optimizing indoor environments, its computational cost limits rapid exploration.

By Chris R. Jung, Markus D\"orr, Natalie J\"ungling, Jennifer Niessner, Adam T. M\"uller, Nicolaj C. Stache
diffusionefficiency
More like this →
arXiv Computer Vision
Oct 16

UltraDiff: Transferring High-Fidelity Priors to Compressed Latent Spaces for High-Resolution Image Generation

UltraDiff is a new framework for high‑resolution image generation with Latent Diffusion Models that tackles the trade‑off between computational cost and fidelity caused by latent compression. It jointly learns latent diffusion and then distills a marginal score using a dual‑branch DiT called MixTeacher, which models both f8 and f32 distributions and resolves compressed‑space ambiguity with high‑fidelity priors. Vector‑field distillation in the native f32 space forces the student model to learn the teacher’s conditional expectation, filtering out compression artifacts and achieving f8‑level quality while retaining f32 efficiency—generating a 2K image in 6.2 seconds on a single A100 GPU, over 40× faster than the f8 baseline.

By Jingjing Ren, Haitian Zheng, Haoyu Chen, Connelly Barnes, Zhifei Zhang, Yuqian Zhou, Zhe Lin, Lei Zhu
diffusionefficiency
More like this →
arXiv Machine Learning
Oct 7

Global Transport Couplings for Classifier-Free Guided Flows

The paper introduces Global Transport (GT), a class‑agnostic optimal‑transport coupling that can be computed without class labels. GT associates different conditions with distinct regions of the source noise, which degrades performance when used without guidance but consistently improves generation when combined with classifier‑free guidance across various domains, model scales, and sampling budgets. The authors argue that coupling design should be evaluated under guided flow conditions rather than unguided generation, and demonstrate GT’s benefits on both discrete class‑conditioned and continuous text‑conditioned image generation.

By Katarina Petrovi\'c, Zander W. Blasingame, Danyal Rehman, \.Ismail \.Ilkan Ceylan, Michael Bronstein, Stephen Y. Zhang, Lazar Atanackovic, Alexander Tong
diffusion
More like this →