arXiv Machine Learning
Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
Jun 29
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.
arXiv AI
Jul 7
Steering Optimisation Trajectories in Diffusion Representation Learning
arXiv:2607. 05319v1 Announce Type: cross Abstract: We study why diffusion autoencoders can achieve similar image quality while learning substantially different latent structures.
arXiv Computer Vision
Aug 24
DiffVC-ONE: Diffusion-based Generative Video Compression with One-Step Video Diffusion Transformer
arXiv:2608.20515v1 Announce Type: new Abstract: Generative video compression can recover rich visual details at low bitrates, but simultaneously achieving high temporal consistency and low inference...
arXiv AI
Jul 20
Toward a mechanistic understanding of inference in visual cortex and diffusion models
arXiv:2607. 15693v1 Announce Type: cross Abstract: We describe a model of perceptual inference in primary visual cortex (V1) equivalent to a minimal diffusion model whose function can be readily understood from its parameters.
arXiv Computer Vision
Sep 22
PixelDiT2: Representation-Grounded Pixel Diffusion Transformers
arXiv:2609.24919v1 Announce Type: new Abstract: Recent advances in pixel-space diffusion models have narrowed the image quality gap with latent-space diffusion, but still converge more slowly and lag...
arXiv AI
Sep 2
V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
V-Co investigates visual co-denoising for pixel-space diffusion models, using a unified JiT-based framework to isolate key design choices. The study identifies two essential components: a dual-stream architecture with flexible cross-stream interaction and a perceptual-drifting hybrid loss combined with RMS-based feature rescaling for stronger semantic supervision. Experiments on ImageNet-256 demonstrate that V-Co surpasses baseline pixel-space diffusion and strong prior pixel-diffusion methods at comparable model sizes while requiring fewer training epochs.