arXiv Computer Vision
Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
3d ago
D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders
D‑Scope is a framework that links the interpretation of sparse autoencoder (SAE) features in diffusion transformers (DiTs) to controllable image generation. It aggregates SigLIP‑2 embeddings of highly activating image patches into visual centroids, matches target text descriptions against these centroids, and retrieves individual features without per‑feature text annotations. The method provides visual evidence for each selection and uses spatially masked interventions to test decoder directions under fixed generation conditions, evaluated across 150 SAEs and a benchmark of 100 target concepts.
arXiv Computer Vision
Sep 2
Advanced Pixel Diffusion Model with Guided Sparse Global Refinement
arXiv:2609.00798v1 Announce Type: new Abstract: Pixel-space diffusion has recently emerged as a promising direction for high-fidelity image generation by modeling images directly in the original pixe...
Hugging Face Trending Papers
Sep 1
Advanced Pixel Diffusion Model with Guided Sparse Global Refinement
Pixel-space diffusion has recently emerged as a promising direction for high-fidelity image generation by modeling images directly in the original pixel domain. However, pixel-space diffusion is compu...
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.
arXiv Computer Vision
Sep 24
UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
UVU is a vision-language unified autoregressive framework that integrates visual supervision directly into the pre-training stage of multimodal large language models. By using continuous visual encoding and a large-scale iterative hierarchical clustering algorithm to build a pixel-level visual codebook, UVU enables lossless representation of visual inputs and autoregressive generation of pixel-level image tokens alongside textual tokens. This approach synergizes pixel-level visual perception with semantic-level visual understanding, allowing models to internalize visual reconstruction capabilities and improve multimodal understanding performance.
arXiv AI
Jul 8
Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers
arXiv:2605. 13974v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood.