Boris van Breugel
12 papers · 2021–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Conference Polyglot (6) πΊοΈ Taxonomy Completionist (11) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (13)
π€
Dynamic Duo
(10)
π₯
Unstoppable
(5)
π
Century Club
(12)
β
The Questioner
(3)
Conferences
ICML (5)
NIPS (3)
AISTATS (1)
EACL (1)
ECCV (1)
ICLR (1)
Top co-authors
Research topics
Keywords
generative model
(3)
synthetic datum
(2)
density estimation
(1)
uncertainty quantification
(1)
model evaluation
(1)
distribution shift
(1)
posterior approximation
(1)
bias mitigation
(1)
downstream task
(1)
overfitting detection
(1)
membership inference
(1)
language model fine-tuning
(1)
membership inference attack
(1)
deep ensemble
(1)
gender bia
(1)
pronoun resolution
(1)
precision-recall analysis
(1)
diversity assessment
(1)
sample-level evaluation
(1)
model auditing
(1)
Papers
Position: All Current Generative Fidelity and Diversity Metrics are Flawed
ICML 2025
Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
ICLR 2024
RadEdit: stress-testing biomedical vision models via diffusion image editing
ECCV 2024
Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes
ICML 2024
Position: Why Tabular Foundation Models Should Be a Research Priority
ICML 2024
Synthetic Data, Real Errors: How (Not) to Publish and Use Synthetic Data
ICML 2023
Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data
NIPS 2023
What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization
NIPS 2023
Membership Inference Attacks against Synthetic Data through Overfitting Detection
AISTATS 2023
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models
ICML 2022
DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
NIPS 2021
Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models
EACL 2021