25 citations · 90 across the 12 of their papers we have counts for
12 papers
MobileWan: Closing the Quality Gap for Mobile Video Diffusion
Mohsen Ghafoorian, Denis Korzhenkov, Adil Karjauv +9
Recent advances in video diffusion have been driven by scaling transformer-based architectures to billions of parameters, substantially improving visual fidelity and motion coheren…
FPTQuant: Function-Preserving Transforms for LLM Quantization
Boris van Breugel, Yelysei Bondarenko, Paul Whatmough +1
Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective at improving efficiency, naive q…
LaTable: Towards Large Tabular Models
Boris van Breugel, Jonathan Crabbé, Rob Davis +1
Tabular data is one of the most ubiquitous modalities, yet the literature on tabular generative foundation models is lagging far behind its text and vision counterparts. Creating s…
Why Tabular Foundation Models Should Be a Research Priority
Boris van Breugel, Mihaela van der Schaar
Recent text and image foundation models are incredibly impressive, and these models are attracting an ever-increasing portion of research resources. In this position piece we aim t…
Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes
Nabeel Seedat, Nicolas Huynh, Boris van Breugel +1
Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem. Hence, data augmentation methods to increase the sample size of datasets needed for ML a…
Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data
Boris van Breugel, Nabeel Seedat, Fergus Imrie +1
Evaluating the performance of machine learning models on diverse and underrepresented subgroups is essential for ensuring fairness and reliability in real-world applications. Howev…
Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
Yangming Li, Boris van Breugel, Mihaela van der Schaar
Because diffusion models have shown impressive performances in a number of tasks, such as image synthesis, there is a trend in recent works to prove (with certain assumptions) that…
The Spherical Grasshopper Problem
Boris van Breugel
The aim of this essay is to better understand the Grasshopper Problem on the surface of the unit sphere. The problem is motivated by analysing Bell inequalities, but can be formula…
Synthetic data, real errors: how (not) to publish and use synthetic data
Boris van Breugel, Zhaozhi Qian, Mihaela van der Schaar
Generating synthetic data through generative models is gaining interest in the ML community and beyond, promising a future where datasets can be tailored to individual needs. Unfor…
Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data
Boris van Breugel, Mihaela van der Schaar
Generating synthetic data through generative models is gaining interest in the ML community and beyond. In the past, synthetic data was often regarded as a means to private data re…
Membership Inference Attacks against Synthetic Data through Overfitting Detection
Boris van Breugel, Hao Sun, Zhaozhi Qian +1
Data is the foundation of most science. Unfortunately, sharing data can be obstructed by the risk of violating data privacy, impeding research in fields like healthcare. Synthetic…
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models
Ahmed M. Alaa, Boris van Breugel, Evgeny Saveliev +1
Devising domain- and model-agnostic evaluation metrics for generative models is an important and as yet unresolved problem. Most existing metrics, which were tailored solely to the…