PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
cs.CV
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
- SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models
- BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
- PixelFlow: Pixel-Space Generative Models with Flow
- LayerSync: Self-aligning Intermediate Layers
- Dilated Neighborhood Attention Transformer
- Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
- Classifier-Free Diffusion Guidance
- ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
- Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders
- There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training
- Back to Basics: Let Denoising Generative Models Denoise
- V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising
- Efficient Generative Model Training via Embedded Representation Warmup
- DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
- PixelGen: Improving Pixel Diffusion with Perceptual Supervision
- DINOv2: Learning Robust Visual Features without Supervision
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- SAM 2: Segment Anything in Images and Videos
- Representation Alignment for Just Image Transformers is not Easier than You Think
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models