Boris van Breugel

31 papers A* 8A 2Journal 19Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Dissecting Quantization Error: A Concentration-Alignment Perspective. CoRR Marco Federici, Boris van Breugel, Paul N. Whatmough, Markus Nagel
2025	J	`jnl`	FPTQuant: Function-Preserving Transforms for LLM Quantization. CoRR Boris van Breugel, Yelysei Bondarenko, Paul N. Whatmough, Markus Nagel
2025	J	`jnl`	HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations. CoRR Marco Federici, Riccardo Del Chiaro, Boris van Breugel, Paul N. Whatmough, Markus Nagel
2025	—	`conf`	Position: All Current Generative Fidelity and Diversity Metrics are Flawed. ICML (Position Papers) Ossi Räisä, Boris van Breugel, Mihaela van der Schaar
2025	J	`jnl`	Position: All Current Generative Fidelity and Diversity Metrics are Flawed. CoRR Ossi Räisä, Boris van Breugel, Mihaela van der Schaar
2025	J	`jnl`	STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization. CoRR Marco Federici, Riccardo Del Chiaro, Boris van Breugel, Paul N. Whatmough, Markus Nagel
2024	A*	`conf`	Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes. ICML Nabeel Seedat, Nicolas Huynh, Boris van Breugel, Mihaela van der Schaar
2024	J	`jnl`	LaTable: Towards Large Tabular Models. CoRR Boris van Breugel, Jonathan Crabbé, Rob Davis, Mihaela van der Schaar
2024	A*	`conf`	Position: Why Tabular Foundation Models Should Be a Research Priority. ICML Boris van Breugel, Mihaela van der Schaar
2024	—	`conf`	RadEdit: Stress-Testing Biomedical Vision Models via Diffusion Image Editing. ECCV (12) Fernando Pérez-García, Sam Bond-Taylor, Pedro P. Sanchez, Boris van Breugel, Daniel C. Castro, Harshita Sharma, Valentina Salvatelli, Maria T. A. Wetscherek, Hannah Richardson, Matthew P. Lungren, Aditya V. Nori, Javier Alvarez-Valle, Ozan Oktay, Maximilian Ilse
2024	A*	`conf`	Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models. ICLR Yangming Li, Boris van Breugel, Mihaela van der Schaar
2024	J	`jnl`	Why Tabular Foundation Models Should Be a Research Priority. CoRR Boris van Breugel, Mihaela van der Schaar
2023	J	`jnl`	Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data. CoRR Boris van Breugel, Mihaela van der Schaar
2023	A*	`conf`	Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data. NeurIPS Boris van Breugel, Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar
2023	J	`jnl`	Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data. CoRR Boris van Breugel, Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar
2023	J	`jnl`	Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in ultra low-data regimes. CoRR Nabeel Seedat, Nicolas Huynh, Boris van Breugel, Mihaela van der Schaar
2023	A	`conf`	Membership Inference Attacks against Synthetic Data through Overfitting Detection. AISTATS Boris van Breugel, Hao Sun, Zhaozhi Qian, Mihaela van der Schaar
2023	J	`jnl`	Membership Inference Attacks against Synthetic Data through Overfitting Detection. CoRR Boris van Breugel, Hao Sun, Zhaozhi Qian, Mihaela van der Schaar
2023	J	`jnl`	RadEdit: stress-testing biomedical vision models via diffusion image editing. CoRR Fernando Pérez-García, Sam Bond-Taylor, Pedro P. Sanchez, Boris van Breugel, Daniel C. Castro, Harshita Sharma, Valentina Salvatelli, Maria T. A. Wetscherek, Hannah Richardson, Matthew P. Lungren, Aditya V. Nori, Javier Alvarez-Valle, Ozan Oktay, Maximilian Ilse
2023	J	`jnl`	Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models. CoRR Yangming Li, Boris van Breugel, Mihaela van der Schaar
2023	A*	`conf`	Synthetic Data, Real Errors: How (Not) to Publish and Use Synthetic Data. ICML Boris van Breugel, Zhaozhi Qian, Mihaela van der Schaar
2023	J	`jnl`	Synthetic data, real errors: how (not) to publish and use synthetic data. CoRR Boris van Breugel, Zhaozhi Qian, Mihaela van der Schaar
2023	A*	`conf`	What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization. NeurIPS Hao Sun, Boris van Breugel, Jonathan Crabbé, Nabeel Seedat, Mihaela van der Schaar
2022	J	`jnl`	DAUX: a Density-based Approach for Uncertainty eXplanations. CoRR Hao Sun, Boris van Breugel, Jonathan Crabbé, Nabeel Seedat, Mihaela van der Schaar
2022	A*	`conf`	How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models. ICML Ahmed M. Alaa, Boris van Breugel, Evgeny S. Saveliev, Mihaela van der Schaar
2022	J	`jnl`	Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes. CoRR Tennison Liu, Alex J. Chan, Boris van Breugel, Mihaela van der Schaar
2021	A*	`conf`	DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks. NeurIPS Boris van Breugel, Trent Kyono, Jeroen Berrevoets, Mihaela van der Schaar
2021	J	`jnl`	DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks. CoRR Boris van Breugel, Trent Kyono, Jeroen Berrevoets, Mihaela van der Schaar
2021	J	`jnl`	How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models. CoRR Ahmed M. Alaa, Boris van Breugel, Evgeny Saveliev, Mihaela van der Schaar
2021	A	`conf`	Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models. EACL Daniel de Vassimon Manela, David Errington, Thomas Fisher, Boris van Breugel, Pasquale Minervini
2021	J	`jnl`	Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models. CoRR Daniel de Vassimon Manela, David Errington, Thomas Fisher, Boris van Breugel, Pasquale Minervini