arXiv Machine Learning June 9, 2026 By Berker Demirel, Valentino Maiorca, Marco Fumero, Theofanis Karaletsos, Francesco Locatello

Assessing Sample Quality in Conditional Generation under Compositional Shift

Read the original on arXiv Machine Learning →

arXiv:2606. 09601v1 Announce Type: new Abstract: Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimental factors.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

Aug 11

Tokenizer Generator Coupling in Medical Image Generation

arXiv:2608. 07713v1 Announce Type: cross Abstract: Latent medical image generators usually treat the tokenizer as fixed preprocessing.

By Liam Chalcroft

diffusion nlp

arXiv AI

Jul 7

Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting

arXiv:2607. 02637v1 Announce Type: cross Abstract: Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models.

By Disheng Liu, Tuo Liang, Chaoda Song, Yu Yin

llms computer-vision fine-tuning benchmarks safety

arXiv Computer Vision

Aug 25

AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection

arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specif...

By Yichen Jiang, Mohammed Talha Alam, Sohail Ahmed Khan, Duc-Tien Dang-Nguyen, Fakhri Karray

llms diffusion fine-tuning benchmarks safety

arXiv AI

Jul 17

Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers

arXiv:2607. 14984v1 Announce Type: new Abstract: Per-subgroup fairness audits of medical image classifiers face a sample-size problem: minority subgroups in held-out test sets have so few samples that the resulting confidence intervals on per-subgroup performance are wider than the bias the audit is meant to detect.

By Mahmoud Ibrahim, Bart Elen, Chang Sun, Gokhan Ertaylan, Michel Dumontier

diffusion fine-tuning safety

arXiv AI

Sep 15

To do($x$) or not to do($x$): Medical Image Counterfactuals for Dataset Augmentation

arXiv:2609.14124v1 Announce Type: cross Abstract: Medical image analysis is often hindered by biased datasets, which can lead to biased models and limited clinical applicability. A promising strategy...

By Yasin Ibrahim, Robin J. Evans, Konstantinos Kamnitsas

safety

arXiv Machine Learning

Jul 21

The Label Complexity of Class-Conditional Coverage under Distribution Shift

arXiv:2607. 18088v1 Announce Type: new Abstract: Standard evaluation of many recognition systems contains distribution shift by construction, since benchmarks place disjoint conditions in the training and test splits.

By Weijia Han, Lisha Qu

benchmarks

One email a morning, machine-written

Related stories

Tokenizer Generator Coupling in Medical Image Generation

Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting

AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection

Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers

To do($x$) or not to do($x$): Medical Image Counterfactuals for Dataset Augmentation

The Label Complexity of Class-Conditional Coverage under Distribution Shift