Cover Image

Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bohacek, Matyas, Fel, Thomas, Agrawala, Maneesh, Lubana, Ekdeep Singh
Format:	Preprint
Published:	2025
Subjects:	Graphics Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer
by: Panda, Raina, et al.
Published: (2025)

Human Action CLIPs: Detecting AI-generated Human Motion
by: Bohacek, Matyas, et al.
Published: (2024)

Transparent Image Layer Diffusion using Latent Transparency
by: Zhang, Lvmin, et al.
Published: (2024)

ScriptViz: A Visualization Tool to Aid Scriptwriting based on a Large Movie Database
by: Rao, Anyi, et al.
Published: (2024)

MoVer: Motion Verification for Motion Graphics Animations
by: Ma, Jiaju, et al.
Published: (2025)

Block and Detail: Scaffolding Sketch-to-Image Generation
by: Sarukkai, Vishnu, et al.
Published: (2024)

Instance Segmentation of Scene Sketches Using Natural Image Priors
by: Tang, Mia, et al.
Published: (2025)

Mixture of Contexts for Long Video Generation
by: Cai, Shengqu, et al.
Published: (2025)

Nepotistically Trained Generative-AI Models Collapse
by: Bohacek, Matyas, et al.
Published: (2023)

Synthetic Human Action Video Data Generation with Pose Transfer
by: Knapp, Vaclav, et al.
Published: (2025)

Can Pose Transfer Models Generate Realistic Human Motion?
by: Knapp, Vaclav, et al.
Published: (2025)

GenAI Confessions: Black-box Membership Inference for Generative Image Models
by: Bohacek, Matyas, et al.
Published: (2025)

Improved Baselines with Representation Autoencoders
by: Singh, Jaskirat, et al.
Published: (2026)

ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
by: Liu, Fangfu, et al.
Published: (2024)

DreamDrive: Generative 4D Scene Modeling from Street View Images
by: Mao, Jiageng, et al.
Published: (2024)

BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities in Pretrained Diffusion Models
by: Purushwalkam, Senthil, et al.
Published: (2024)

GazeFusion: Saliency-Guided Image Generation
by: Zhang, Yunxiang, et al.
Published: (2024)

SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
by: Liu, Yuan, et al.
Published: (2023)

Materialist: Physically Based Editing Using Single-Image Inverse Rendering
by: Wang, Lezhong, et al.
Published: (2025)

Object-level Visual Prompts for Compositional Image Generation
by: Parmar, Gaurav, et al.
Published: (2025)

A Survey on Quality Metrics for Text-to-Image Generation
by: Hartwig, Sebastian, et al.
Published: (2024)

Make It Count: Text-to-Image Generation with an Accurate Number of Objects
by: Binyamin, Lital, et al.
Published: (2024)

GraphicsDreamer: Image to 3D Generation with Physical Consistency
by: Chen, Pei, et al.
Published: (2024)

Dataset of News Articles with Provenance Metadata for Media Relevance Assessment
by: Peterka, Tomas, et al.
Published: (2025)

Image Generation Models: A Technical History
by: Shirvani, Rouzbeh
Published: (2026)

MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation
by: Wang, Kuan-Chieh, et al.
Published: (2024)

Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision
by: Feuerpfeil, Moritz, et al.
Published: (2024)

Annotated Hands for Generative Models
by: Yang, Yue, et al.
Published: (2024)

SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder
by: Kamenetsky, Ronen, et al.
Published: (2025)

SparseOIT: Improving Order-Independent Transparency 3DGS via Active Set Method
by: Yang, Wentao, et al.
Published: (2026)

SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views
by: Xu, Chao, et al.
Published: (2024)

WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions
by: Li, Zizhang, et al.
Published: (2025)

Multimodal Cinematic Video Synthesis Using Text-to-Image and Audio Generation Models
by: S, Sridhar, et al.
Published: (2025)

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
by: Guo, Yuwei, et al.
Published: (2023)

DragPoser: Motion Reconstruction from Variable Sparse Tracking Signals via Latent Space Optimization
by: Ponton, Jose Luis, et al.
Published: (2024)

VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model
by: Zuo, Qi, et al.
Published: (2024)

ReLumix: Extending Image Relighting to Video via Video Diffusion Models
by: Wang, Lezhong, et al.
Published: (2025)

FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Clothing Images
by: Zhang, Cheng, et al.
Published: (2024)

TEXGen: a Generative Diffusion Model for Mesh Textures
by: Yu, Xin, et al.
Published: (2024)

Transcending Dimensions using Generative AI: Real-Time 3D Model Generation in Augmented Reality
by: Behravan, Majid, et al.
Published: (2025)