Cover Image

Unified Latents (UL): How to train your latents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Heek, Jonathan, Hoogeboom, Emiel, Mensink, Thomas, Salimans, Tim
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multistep Distillation of Diffusion Models via Moment Matching
by: Salimans, Tim, et al.
Published: (2024)

Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD
by: Hoogeboom, Emiel, et al.
Published: (2026)

Multistep Consistency Models
by: Heek, Jonathan, et al.
Published: (2024)

Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
by: Bartosh, Grigory, et al.
Published: (2026)

Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion
by: Hoogeboom, Emiel, et al.
Published: (2024)

Blurring Diffusion Models
by: Hoogeboom, Emiel, et al.
Published: (2022)

Model Integrity when Unlearning with T2I Diffusion Models
by: Schioppa, Andrea, et al.
Published: (2024)

Rolling Diffusion Models
by: Ruhe, David, et al.
Published: (2024)

Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variations
by: Kumar, Manoj, et al.
Published: (2024)

Covariance-aware sampling for Diffusion Models
by: Schioppa, Andrea, et al.
Published: (2026)

How to train your ViT for OOD Detection
by: Mueller, Maximilian, et al.
Published: (2024)

DORSal: Diffusion for Object-centric Representations of Scenes et al
by: Jabri, Allan, et al.
Published: (2023)

High-Fidelity Image Compression with Score-based Generative Models
by: Hoogeboom, Emiel, et al.
Published: (2023)

Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets
by: Ngnawe, Jonas, et al.
Published: (2023)

HAMMR: HierArchical MultiModal React agents for generic VQA
by: Castrejon, Lluis, et al.
Published: (2024)

Don't drop your samples! Coherence-aware training benefits Conditional diffusion
by: Dufour, Nicolas, et al.
Published: (2024)

UL-DD: A Multimodal Drowsiness Dataset Using Video, Biometric Signals, and Behavioral Data
by: Bodaghi, Morteza, et al.
Published: (2025)

HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
by: Choi, Sungik, et al.
Published: (2024)

LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
by: Jin, Jiachun, et al.
Published: (2026)

How to train your VAE
by: Rivera, Mariano
Published: (2023)

Unifying Image Counterfactuals and Feature Attributions with Latent-Space Adversarial Attacks
by: Goldwasser, Jeremy, et al.
Published: (2025)

What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
by: Thomas, Xavier, et al.
Published: (2025)

Motus: A Unified Latent Action World Model
by: Bi, Hongzhe, et al.
Published: (2025)

UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models
by: Wang, Yimu, et al.
Published: (2025)

Latent Danger Zone: Distilling Unified Attention for Cross-Architecture Black-box Attacks
by: Li, Yang, et al.
Published: (2025)

Exploring possible vector systems for faster training of neural networks with preconfigured latent spaces
by: Gabdullin, Nikita
Published: (2025)

Unified Framework for Pre-trained Neural Network Compression via Decomposition and Optimized Rank Selection
by: Aghababaei-Harandi, Ali, et al.
Published: (2024)

Robustly overfitting latents for flexible neural image compression
by: Perugachi-Diaz, Yura, et al.
Published: (2024)

Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers
by: Schmidt, Johann, et al.
Published: (2024)

How Does the Spatial Distribution of Pre-training Data Affect Geospatial Foundation Models?
by: Purohit, Mirali, et al.
Published: (2025)

A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data & Overparameterization?
by: Xiao, Tim Z., et al.
Published: (2023)

How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions
by: Brack, Manuel, et al.
Published: (2025)

OCT Data is All You Need: How Vision Transformers with and without Pre-training Benefit Imaging
by: Han, Zihao, et al.
Published: (2025)

Fine-tuning can cripple your foundation model; preserving features may be the solution
by: Mukhoti, Jishnu, et al.
Published: (2023)

Efficient training for compact compression models via sequential distillation
by: Rodrigues, Caroline Mazini, et al.
Published: (2026)

JLT: Clean-Latent Prediction in Latent Diffusion Transformers
by: Fu, Funing, et al.
Published: (2026)

Latent Diffusion Inversion Requires Understanding the Latent Space
by: Rao, Mingxing, et al.
Published: (2025)

LatentGAN Autoencoder: Learning Disentangled Latent Distribution
by: Kalwar, Sanket, et al.
Published: (2022)

Using predefined vector systems as latent space configuration for neural network supervised training on data with arbitrarily large number of classes
by: Gabdullin, Nikita
Published: (2025)

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
by: Yu, Sihyun, et al.
Published: (2025)