Presentations

2025

• Tutorial. (upcoming, September) "Combining language and vision with VLMs" (tentative title). CLiC-it 2025. Cagliari, Italy.
• Poster. (upcoming, July) "From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions". ACL 2025. Vienna, Austria.
• Invited talk. March 26. CLASP Seminar, University of Gothenburg, Gothenburg, Sweden. "Not (yet) the whole story: The need for human-like evaluation of visual LLMs in multimodal communicative tasks".
• Invited talk. January 30. Human-Centered Data Science group, University of Göttingen, Göttingen, Germany. "Dealing with underspecified language: A semantic challenge for large language models."
• Talk. January 20. The First Workshop of Evaluation of Multi-Modal Generation (EvalMG) at COLING, Abu Dhabi, UAE. "If I feel smart, I will do the right thing: Combining Complementary Multimodal Information in Visual Language Models."

2024

• Keynote talk. November 28. Fine-grained Evaluation of Vision and Language Models (FINE) workshop at AI*IA 2024, Bolzano, Italy. "Not (yet) the whole story: The need for human-like evaluation of visual LLMs in multimodal communicative tasks".
• Invited talk. October 29. Dealing with Meaning Variation in NLP (DeMeVa2) 2024, Utrecht, Netherlands. "Implicit and Underspecified Language as a Communicative Testbed for Large Language Models".
• Invited talk. October 18. Generative AI in Future HRM, Amsterdam People Analytics Centre, University of Amsterdam, Amsterdam, Netherlands. "Gen-AI and the future of HRM: Open challenges from NLP".
• Keynote talk. October 1. Perspectives in NLP x Humanities, Cognition, and Social Sciences, Interacting Minds Centre, Aarhus University, Denmark. "Implicit and Underspecified Language as a Communicative Testbed for Large Language Models".
• Keynote talk. September 13. MultiplEYE Mid-Term Conference (MuMiCo) 2024. "Leveraging gaze data in image description generation: Towards more human-like visually-grounded NLP models".
• Keynote talk. August 15. Cognitive Modeling and Computational Linguistics (CMCL) at ACL 2024, Bangkok, Thailand. "From semantic understanding to human-like communication: Implicit and underspecified language as a testbed for large language models".
• Invited talk. May 24. Tilburg University, Tilburg, Netherlands. "Dealing with implicit and underspecified language: A semantic challenge for large language models".
• Invited talk. April 23. Uva AI x Cultural Production Seminar, Amsterdam, Netherlands. "Large Language Models as Interlocutors: Between Reliability and Deconstruction".
• Invited talk. April 5. Fluido, Woerden, Netherlands. "From NLP to General Intelligence: Directions and Open Challenges".
• Invited talk. March 13. HWU iLab, Heriot-Watt, Edinburgh, Scotland. "From Word Representation to Communicative Success: Beyond Image-Text Alignment in Language-and-Vision Modeling".
• Invited talk. February 28. COLT Seminar, UPF, Barcelona, Spain. "Dealing with implicit and underspecified language: A semantic challenge for large language models".
• Invited talk. February 26. Amazon, Barcelona, Spain. "Dealing with implicit and underspecified language: A semantic challenge for large language models".
• Talk. January 25. Using computational models to bridge between neurobiology, psychology, and linguistic theory workshop, Nijmegen, Netherlands. "A Psycholinguistic Analysis of BERT's Representations of Compounds".
• Poster. January 11. HumanCLAIM workshop, VU Amsterdam, Netherlands. "A Psycholinguistic Analysis of BERT's Representations of Compounds".

2023

• Invited talk. November 3. Groningen Reading Group, Groningen, Netherlands. "From Word Representation to Communicative Success".
• Keynote talk. September 22. LIMO workshop co-located with KONVENS, Ingolstadt, Germany. "From Word Representation to Communicative Success: The Need for Semantic and Pragmatic Analysis in Visually Grounded Language Processing".
• Keynote talk. September 12. MM-NLG workshop co-located with INLG and SIGDial, Prague, Czech Republic. "Adaptation in the Realm of Visually Grounded Language: Of Speakers, Models, and Tasks".
• Poster. July 11. ACL, Toronto, Canada. "Dealing with Semantic Underspecification in Multimodal NLP".
• Invited talk. July 5. CBS Research Seminar, Hong Kong Polytechnic University, online. "Semantic representations of words in (multimodal) masked language models".
• Invited talk. June 15. eScience Center, Amsterdam. "Semantic representations of words in (multimodal) masked language models".
• Talk & Poster. May 3-4. EACL, Dubrovnik, Croatia. "A Psycholinguistic Analysis of BERT's Representations of Compounds".
• Dissemination talk. April 2. University of Amsterdam. "A morning with ChatGPT: A discussion of generative language models and its impact on the university" with Jelle Zuidema, Jelke Bloem, and Marjolein Lanzing.
• Dissemination talk. January 24. University of Amsterdam. "An afternoon with ChatGPT" with Jelle Zuidema, Jelke Bloem, and Raquel Fernández.

2022

• Invited talk. November, 23. CONVERSATIONS, Amsterdam, Netherlands. "Controllable Text Generation for All Ages: Evaluating a Plug-and-Play Approach to Age-Adapted Dialogue".
• Talk. June, 30. CLIC-it, Milan, Italy. "Detecting Age-Related Linguistic Patterns in Dialogue: Toward Adaptive Conversational Systems".
• Invited talk. June, 22. BILS Seminar, University of Milano-Bicocca, online. "Modeling gradable adjectives leveraging visual contexts".
• Talk & Poster. May, 23-25. ACL, Dublin, Ireland. "Word Representation Learning in Multimodal Pre-Trained Transformers: An Intrinsic Evaluation".
• Invited talk. May, 17. CoSaQ final workshop, University of Amsterdam. "Semantic adaptation through active information seeking: A case study on gradable adjectives".
• Invited talk. March, 7. CIMeC - University of Trento, Rovereto. "Visually-grounded semantics in multimodal Transformers (and humans)".

2021

• Talk. December, 14. ILLC Colloquium, UvA, online. "Visually-grounded semantics in deep neural networks (and humans)".
• Talk. June, 21. Three talks on topics in AI, UvA, online. "Integration of language and vision in multimodal pre-trained Transformers".
• Talk. May, 7. MLC seminar, UvA, online. "Semantic adaptation to the interpretation of gradable adjectives via passive exposure and active information seeking".
• Talk. March, 18. TAB meeting, online. "Be Different to Be Better! A Benchmark to Leverage the Complementarity of Language and Vision".
• Poster. February, 24-25. ELLIS NLP workshop, online. "Be Different to Be Better! A Benchmark to Leverage the Complementarity of Language and Vision".

2020

• Poster. November, 20. BlackBoxNLP at EMNLP, online. "Be Different to Be Better! A Benchmark to Leverage the Complementarity of Language and Vision".
• Talk November, 17. EMNLP, online. "Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts" (Joint presentation w/ E. Takmaz, M. Giulianelli, A. Sinclair, R. Fernández).
• Poster. July, 30. CogSci, online. "Asking questions with a big impact: Adapting to other interpretations of gradable adjectives".
• Poster. May, 18. GeCKo symposium, online. "Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts".
• Invited talk. February, 17. COLT Seminar, Barcelona, Spain. "Modeling Gradable Adjectives Leveraging Visual Contexts".

2019

• Talk. November, 6. EMNLP-IJCNLP, Hong Kong. "Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts".
• Poster. November, 3. LANTERN at EMNLP-IJCNLP, Hong Kong. "Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size".
• Poster. August, 30. Interactive Minds, Egmond aan Zee, The Netherlands. "MALeViC: Modeling Adjectives Leveraging Visual Contexts".
• Talk. May, 6. BlackBoxNL, 's-Hertogenbosch, The Netherlands. "Exploring (Multimodal) Model Abilities in Grounding Vague Expressions".
• Talk. April, 2. ILLC Computational Linguistics Seminars, Amsterdam, The Netherlands. "Grounding Vague Expressions in Vision".

2018

• Poster. September, 8. SiVL workshop at ECCV, Munich, Germany. "Be Different to Be Better: Toward the Integration of Language and Vision".
• Poster. September, 7. SAP Machine Learning Retreat, Munich, Germany. "Be Different to Be Better: Toward the Integration of Language and Vision".
• Talk. June, 2. NAACL-HLT, New Orleans, USA. "Comparatives, Quantifiers, Proportions: A Multi-Task Model for the Learning of Quantities from Vision".
• Poster. May, 5. CAOS, Rovereto, Italy. "Comparatives, Quantifiers, Proportions: A Multi-Task Model for the Learning of Quantities from Vision".
• Talk. March, 2. CIMeC Brown Bag, Rovereto, Italy. "Cognitively-Inspired Quantification in Vision: A Deep Learning Approach".

2017

• Invited talk. November, 15. AMORE Seminar, Barcelona, Spain. "Learning to Quantify from Language and Vision: Insights from Behavioral and Computational Studies".
• Invited talk. October, 24. ILLC Computational Linguistics Seminars, Amsterdam, The Netherlands. "Learning to Quantify from Language and Vision: Insights from Behavioral and Computational Studies".
• Invited talk. September, 28. CoSaQ kick-off workshop, Amsterdam, The Netherlands. "Quantifiers and Proportions in Language and Vision: Insights from Behavioral and Computational Studies" (Joint presentation w/ Raffaella Bernardi).
• Poster. September, 26. Google NLP Summit, Zurich, Switzerland. "Be Precise or Fuzzy: Learning the Meaning of Cardinals and Quantifiers from Vision".
• Talk. May, 5. Lectures on Computational Linguistics, Pavia, Italy. "Learning Quantity Expressions from Language and Vision".
• Poster. April, 5. EACL, Valencia, Spain. "Be Precise or Fuzzy: Learning the Meaning of Cardinals and Quantifiers from Vision".
• Poster. April, 3. CMCL at EACL, Valencia, Spain. "Be Precise or Fuzzy: Learning the Meaning of Cardinals and Quantifiers from Vision".

2016

• Talk. December, 5. CLIC-it, Naples, Italy. "Learning to Quantify from Images".
• Talk & Poster. August, 12. VL at ACL, Berlin, Germany. "Building a Bagpipe with a Bag and a Pipe: Exploring Conceptual Combination in Vision".
• Talk & Poster. August, 12. VL at ACL, Berlin, Germany. "'Look, some green circles!': Learning to Quantify from Images".
• Poster. July, 8. 5th CogEvo, Rovereto, Italy. "The Approximate Number System of an Artificial Neural Network".
• Poster. May, 5. Psycholinguistics in Flanders, Antwerpen, Belgium. "Lexical families in Vision".
• Poster. March, 21. iV&L Net Training School, Malta. "Lexical families in Vision".

2015

• Talk. July, 12. First Quantitative Morphology Meeting, Belgrade, Serbia. "Capturing different classes of compound words: A new perspective from compositional distributional semantics".