Multi-modal Learning Algorithms for Sequence Modeling and Representation Learning [UvA-Dare]
PhD Thesis 2024 - University of Amsterdam
Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning [OpenReview] [Github]
Published in TMLR 2024 - Transactions on Machine Learning Research
Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition [Arxiv]
Published in Proceedings of INTERSPEECH 2023 - Annual Conference of the International Speech Communication Association
Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval [OpenReview] [Github] [Video]
Published in TMLR 2023 - Transactions on Machine Learning Research
A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing [Arxiv] [Github]
Published in Proceedings of HHAI 2022 - International Conference on Hybrid Human-Machine Intelligence
Do Lessons from Metric Learning Generalize to Image-Caption Retrieval? [Arxiv] [Github] [Slides]
Published in Proceedings of ECIR 2022 - European Conference on Information Retrieval
Extending CLIP for Category-to-image Retrieval in E-commerce [Arxiv]
Published in Proceedings of ECIR 2022 - European Conference on Information Retrieval
Reproducibility as a Mechanism for Teaching Fairness, Accountability, Confidentiality, and Transparency in Artificial Intelligence [Arxiv]
In EAAI 2022 - AAAI Symposium on Educational Advances in Artificial Intelligence
Order in the Court: Explainable AI Methods Prone to Disagreement [Arxiv] [Github] [Video]
In the ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI
Conditional Image Generation and Manipulation for User-Specified Content [Arxiv]
In the CVPR workshop on AI for Content Creation workshop on AI for Content Creation