Imagen de Portada

One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Surkov, Viacheslav, Wendler, Chris, Mari, Antonio, Terekhov, Mikhail, Deschenaux, Justin, West, Robert, Gulcehre, Caglar, Bau, David
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Promises, Outlooks and Challenges of Diffusion Language Modeling
por: Deschenaux, Justin, et al.
Publicado: (2024)

BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers
por: Deschenaux, Justin, et al.
Publicado: (2026)

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
por: Deschenaux, Justin, et al.
Publicado: (2024)

In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning
por: Terekhov, Mikhail, et al.
Publicado: (2024)

The Diffusion Duality, Chapter II: $Ψ$-Samplers
por: Deschenaux, Justin, et al.
Publicado: (2026)

Partition Generative Modeling: Masked Modeling Without Masks
por: Deschenaux, Justin, et al.
Publicado: (2025)

Self-Recognition in Language Models
por: Davidson, Tim R., et al.
Publicado: (2024)

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall
por: Jo, Mingyu, et al.
Publicado: (2025)

Control Tax: The Price of Keeping AI in Check
por: Terekhov, Mikhail, et al.
Publicado: (2025)

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
por: Liu, Xingchao, et al.
Publicado: (2023)

Controlling Latent Diffusion Using Latent CLIP
por: Becker, Jason, et al.
Publicado: (2025)

RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference
por: Wei, Xiuying, et al.
Publicado: (2026)

Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards
por: Karzanov, Daniil, et al.
Publicado: (2025)

OSV: One Step is Enough for High-Quality Image to Video Generation
por: Mao, Xiaofeng, et al.
Publicado: (2024)

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
por: Terekhov, Mikhail, et al.
Publicado: (2025)

SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation
por: Nguyen, Thuan Hoang, et al.
Publicado: (2023)

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
por: Tian, Zhihua, et al.
Publicado: (2025)

One-Step Diffusion for Perceptual Image Compression
por: Jia, Yiwen, et al.
Publicado: (2026)

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
por: Tong, Shengbang, et al.
Publicado: (2026)

One-Step Image Translation with Text-to-Image Models
por: Parmar, Gaurav, et al.
Publicado: (2024)

SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion
por: Nguyen, Trong-Tung, et al.
Publicado: (2024)

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
por: Deschenaux, Justin, et al.
Publicado: (2024)

Augmenting Attention with Exponentially Decaying Memory Improves Query-Aware KV Sparsity
por: Wei, Xiuying, et al.
Publicado: (2026)

Distilling Diversity and Control in Diffusion Models
por: Gandikota, Rohit, et al.
Publicado: (2025)

One-Step Diffusion Model for Image Motion-Deblurring
por: Liu, Xiaoyang, et al.
Publicado: (2025)

You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs
por: Luo, Yihong, et al.
Publicado: (2024)

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
por: Dao, Quan, et al.
Publicado: (2024)

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation
por: Selikhanovych, Daniil, et al.
Publicado: (2025)

Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder
por: Wu, Chao, et al.
Publicado: (2025)

Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps
por: Starodubcev, Nikita, et al.
Publicado: (2024)

TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation
por: Huang, Victor Shea-Jay, et al.
Publicado: (2025)

Cyclic Sparse Training: Is it Enough?
por: Gadhikar, Advait, et al.
Publicado: (2024)

Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization
por: Sargent, Kyle, et al.
Publicado: (2025)

Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
por: Zhang, Aiping, et al.
Publicado: (2024)

Discovering Forbidden Topics in Language Models
por: Rager, Can, et al.
Publicado: (2025)

Customizing Text-to-Image Models with a Single Image Pair
por: Jones, Maxwell, et al.
Publicado: (2024)

One-Step Diffusion-Based Image Compression with Semantic Distillation
por: Xue, Naifu, et al.
Publicado: (2025)

Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
por: Xu, Xingqian, et al.
Publicado: (2022)

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
por: Zhao, Chenxi, et al.
Publicado: (2026)

Fleet of Agents: Coordinated Problem Solving with Large Language Models
por: Klein, Lars, et al.
Publicado: (2024)