Cover Image

When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Adamkiewicz, Krzysztof, Moser, Brian Bernhard, Frolov, Stanislav, Nauen, Tobias Christian, Raue, Federico, Dengel, Andreas
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ForAug: Recombining Foregrounds and Backgrounds to Improve Vision Transformer Training with Bias Mitigation
by: Nauen, Tobias Christian, et al.
Published: (2025)

TextTeacher: What Can Language Teach About Images?
by: Nauen, Tobias Christian, et al.
Published: (2026)

Zoomed In, Diffused Out: Towards Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution
by: Moser, Brian B., et al.
Published: (2024)

Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning
by: Moser, Brian B., et al.
Published: (2024)

A Study in Dataset Distillation for Image Super-Resolution
by: Dietz, Tobias, et al.
Published: (2025)

PRISM: Diversifying Dataset Distillation by Decoupling Architectural Priors
by: Moser, Brian B., et al.
Published: (2025)

A Low-Resolution Image is Worth 1x1 Words: Enabling Fine Image Super-Resolution with Transformers and TaylorShift
by: Nagaraju, Sanath Budakegowdanadoddi, et al.
Published: (2024)

Just Leaf It: Accelerating Diffusion Classifiers with Hierarchical Class Pruning
by: Shanbhag, Arundhati S., et al.
Published: (2024)

Hyperspherical Forward-Forward with Prototypical Representations
by: Sarode, Shalini, et al.
Published: (2026)

SubZeroCore: A Submodular Approach with Zero Training for Coreset Selection
by: Moser, Brian B., et al.
Published: (2025)

HyperCore: Coreset Selection under Noise via Hypersphere Models
by: Moser, Brian B., et al.
Published: (2025)

Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution
by: Moser, Brian, et al.
Published: (2023)

Dynamic Attention-Guided Diffusion for Image Super-Resolution
by: Moser, Brian B., et al.
Published: (2023)

Federated Learning for Blind Image Super-Resolution
by: Moser, Brian B., et al.
Published: (2024)

Unlocking Dataset Distillation with Diffusion Models
by: Moser, Brian B., et al.
Published: (2024)

DWA: Differential Wavelet Amplifier for Image Super-Resolution
by: Moser, Brian B., et al.
Published: (2023)

Spherical Dense Text-to-Image Synthesis
by: Winter, Timon, et al.
Published: (2025)

Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
by: Moser, Brian, et al.
Published: (2022)

Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers
by: Nauen, Tobias Christian, et al.
Published: (2023)

A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances
by: Moser, Brian B., et al.
Published: (2025)

Diffusion Models, Image Super-Resolution And Everything: A Survey
by: Moser, Brian B., et al.
Published: (2024)

A Study in Dataset Pruning for Image Super-Resolution
by: Moser, Brian B., et al.
Published: (2024)

LGTM: Training-Free Light-Guided Text-to-Image Diffusion Model via Initial Noise Manipulation
by: Morita, Ryugo, et al.
Published: (2026)

SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time
by: Frolov, Stanislav, et al.
Published: (2024)

ObjBlur: A Curriculum Learning Approach With Progressive Object-Level Blurring for Improved Layout-to-Image Generation
by: Frolov, Stanislav, et al.
Published: (2024)

Multi-Label Scene Classification in Remote Sensing Benefits from Image Super-Resolution
by: Mudraje, Ashitha, et al.
Published: (2025)

When Trust Isn't Enough.
by: Behrman, Sara
Published: (1998)

TKG-DM: Training-free Chroma Key Content Generation Diffusion Model
by: Morita, Ryugo, et al.
Published: (2024)

Word Boundary Information Isn't Useful for Encoder Language Models
by: Gow-Smith, Edward, et al.
Published: (2024)

Inverse Scaling: When Bigger Isn't Better
by: McKenzie, Ian R., et al.
Published: (2023)

TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
by: Nauen, Tobias Christian, et al.
Published: (2024)

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
by: Zhang, Yue, et al.
Published: (2026)

Why Isn't Relational Learning Taking Over the World?
by: Poole, David
Published: (2025)

Frailty Matters—Why Isn't It Guiding Clinical Decisions?
by: Márlon Juliano Romero Aliberti, et al.
Published: (2025)

LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency
by: Morita, Ryugo, et al.
Published: (2026)

When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models
by: Galeone, Cosimo, et al.
Published: (2026)

If It Isn't Broken...Break It!
by: Voges, Mickie A.
Published: (2000)

When Kids Mode Isn't For Kids: Investigating TikTok's "Under 13 Experience"
by: Figueira, Olivia, et al.
Published: (2025)

FedAD-Bench: A Unified Benchmark for Federated Unsupervised Anomaly Detection in Tabular Data
by: Anwar, Ahmed, et al.
Published: (2024)

Normothermic Regional Perfusion: Why Isn't the Lactate Coming Down?
by: Claire Cywes, et al.
Published: (2026)