8 citations · 28 across the 13 of their papers we have counts for
13 papers
Shieldstral
Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273
We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7 its size on text safety benchmarks and set…
Going with the Speed of Sound: Pushing Neural Surrogates into Highly-turbulent Transonic Regimes
Fabian Paischer, Leo Cotteleer, Yann Dreze +5
The widespread use of neural surrogates in automotive aerodynamics, enabled by datasets such as DrivAerML and DrivAerNet++, has primarily focused on bluff-body flows with large wak…
AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformers
Benedikt Alkin, Maurits Bleeker, Richard Kurle +4
Recent advances in neural surrogate modeling offer the potential for transformative innovations in applications such as automotive aerodynamics. Yet, industrial-scale problems ofte…
Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning
Maurits Bleeker, Mariya Hendriksen, Andrew Yates +1
Vision-language models (VLMs) mainly rely on contrastive training to learn general-purpose representations of images and captions. We focus on the situation when one image is assoc…
Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition
Maurits Bleeker, Pawel Swietojanski, Stefan Braun +1
This paper presents an extension to train end-to-end Context-Aware Transformer Transducer ( CATT ) models by using a simple, yet efficient method of mining hard negative phrases fr…
A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing
Michael Neely, Stefan F. Schouten, Maurits Bleeker +1
There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input…
Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval
Maurits Bleeker, Andrew Yates, Maarten de Rijke
To train image-caption retrieval (ICR) methods, contrastive loss functions are a common choice for optimization functions. Unfortunately, contrastive ICR methods are vulnerable to…
Do Lessons from Metric Learning Generalize to Image-Caption Retrieval?
Maurits Bleeker, Maarten de Rijke
The triplet loss with semi-hard negatives has become the de facto choice for image-caption retrieval (ICR) methods that are optimized from scratch. Recent progress in metric learni…
Extending CLIP for Category-to-image Retrieval in E-commerce
Mariya Hendriksen, Maurits Bleeker, Svitlana Vakulenko +3
E-commerce provides rich multimodal data that is barely leveraged in practice. One aspect of this data is a category tree that is being used in search and recommendation. However,…
Reproducibility as a Mechanism for Teaching Fairness, Accountability, Confidentiality, and Transparency in Artificial Intelligence
Ana Lucic, Maurits Bleeker, Sami Jullien +2
In this work, we explain the setup for a technical, graduate-level course on Fairness, Accountability, Confidentiality, and Transparency in Artificial Intelligence (FACT-AI) at the…
Order in the Court: Explainable AI Methods Prone to Disagreement
Michael Neely, Stefan F. Schouten, Maurits J. R. Bleeker +1
By computing the rank correlation between attention weights and feature-additive explanation methods, previous analyses either invalidate or support the role of attention-based exp…
Conditional Image Generation and Manipulation for User-Specified Content
David Stap, Maurits Bleeker, Sarah Ibrahimi +1
In recent years, Generative Adversarial Networks (GANs) have improved steadily towards generating increasingly impressive real-world images. It is useful to steer the image generat…
Bidirectional Scene Text Recognition with a Single Decoder
Maurits Bleeker, Maarten de Rijke
Scene Text Recognition (STR) is the problem of recognizing the correct word or character sequence in a cropped word image. To obtain more robust output sequences, the notion of bid…