Baptiste Caramiaux
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Baptiste Caramiaux has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Jules Françoise
Université Paris-Saclay, CNRS, LISN, Orsay, France
4 shared publications - Sarah Fdili Alaoui
Creative Computing Institute, University of the Arts London, London, United Kingdom
4 shared publications - Téo Sanchez
Ludwig Maximilian University of Munich, Munich, Bavaria, Germany and Munich Center for Digital Sciences and AI (MUC.DAI), Hochschule München University of Applied Sciences, Munich, Bavaria, Germany
3 shared publications - Vaynee Sungeelee
Institut Des Systèmes Intelligents et de Robotique, Sorbonne Université, Institut des Systèmes Intelligents et de Robotique (ISIR), Paris, France
3 shared publications - Antoine Loriette
Sorbonne Université, CNRS, Institut des Systèmes Intelligents et de Robotique (ISIR), France
2 shared publications - Behnoosh Mohammadzadeh
Université Paris Saclay, CNRS, LISN, Orsay, France
2 shared publications
Latest Publications
- Open Access
- 19 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Exploring Normative Behavior in Generative AI: A Case Study of Text-to-Image Systems Using Stable Diffusion
- 19 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessExploring Normative Behavior in Generative AI: A Case Study of Text-to-Image Systems Using Stable Diffusion
- Open Access
- 23 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (6) , 1-31
Designing Accessible Interfaces to Enhance Collective Musical Engagement for and with Children with Autism
Accessible Digital Musical Interfaces (ADMIs) aim to enhance the inclusivity of musical practice by supporting users with diverse needs. This paper focuses on the design and use of ADMIs for and with autistic children. While previous research has highlighted the developmental benefits of ADMIs in therapeutic and educational settings, their potential to foster social interaction and collective musical engagement outside of these contexts remains underexplored. Through an 18-month Action Research collaboration with two non-profit organizations (NPOs) that facilitate creative activities for autistic children, this study investigates the development of ADMIs that support inclusive and collective musical experiences and examines how iterative design processes can respond to the social and relational dynamics specific to group settings involving autistic participants. Our findings highlight the requirements of ADMI design for this context and the evolving role, sometimes ambiguous, that these interfaces play in enabling shared musical engagement. We also reflect on the methodological and ethical challenges of conducting research within NPO environments and promoting the children’s autonomy through open forms of participation, reappropriation and workshop flexibility.
- 23 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (6) , 1-31
Open AccessDesigning Accessible Interfaces to Enhance Collective Musical Engagement for and with Children with Autism
Accessible Digital Musical Interfaces (ADMIs) aim to enhance the inclusivity of musical practice by supporting users with diverse needs. This paper focuses on the design and use of ADMIs for and with autistic children. While previous research has highlighted the developmental benefits of ADMIs in therapeutic and educational settings, their potential to foster social interaction and collective musical engagement outside of these contexts remains underexplored. Through an 18-month Action Research collaboration with two non-profit organizations (NPOs) that facilitate creative activities for autistic children, this study investigates the development of ADMIs that support inclusive and collective musical experiences and examines how iterative design processes can respond to the social and relational dynamics specific to group settings involving autistic participants. Our findings highlight the requirements of ADMI design for this context and the evolving role, sometimes ambiguous, that these interfaces play in enabling shared musical engagement. We also reflect on the methodological and ethical challenges of conducting research within NPO environments and promoting the children’s autonomy through open forms of participation, reappropriation and workshop flexibility.
- 10 September 2026
- Published by Springer Nature
- p. 1-18
Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability
- 10 September 2026
- Published by Springer Nature
- p. 1-18
Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 5135-5139
IR Lens: A Tool for Interpreting Cross-Encoder Models
Transformer-based ranking models, such as MonoBERT, are central to Information Retrieval; yet their inner workings remain largely opaque. This hinders not only our understanding of the systems implementing them, but also our ability to improve them. To alleviate this limitation, we introduce IR Lens, a new interpretability tool tailored to cross-encoders based on two key components: 1) Neuron Integrated Gradients to expose the contributions of model parts at multiple levels, and 2) targeted ablations to support hypothesis tracking. With its interactive graphical interface, IR Lens enables IR practitioners to explore, analyze, and manipulate neuron-level mechanisms in cross-encoders, facilitating a deeper understanding of neural ranking models. By extending the reach of existing interpretability methods, we believe IR Lens has the potential to support the improvement of cross-encoders.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 5135-5139
Open AccessIR Lens: A Tool for Interpreting Cross-Encoder Models
Transformer-based ranking models, such as MonoBERT, are central to Information Retrieval; yet their inner workings remain largely opaque. This hinders not only our understanding of the systems implementing them, but also our ability to improve them. To alleviate this limitation, we introduce IR Lens, a new interpretability tool tailored to cross-encoders based on two key components: 1) Neuron Integrated Gradients to expose the contributions of model parts at multiple levels, and 2) targeted ablations to support hypothesis tracking. With its interactive graphical interface, IR Lens enables IR practitioners to explore, analyze, and manipulate neuron-level mechanisms in cross-encoders, facilitating a deeper understanding of neural ranking models. By extending the reach of existing interpretability methods, we believe IR Lens has the potential to support the improvement of cross-encoders.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Sensemaking in User-Driven Algorithm Auditing: A Case Study on Gender Bias in an Image Captioning Model
Non-experts increasingly engage in user-driven algorithm auditing, interacting directly with AI systems to probe, document, and reflect on biased behavior. Yet, auditing remains challenging due to model opacity and limited support for navigating and interpreting outputs. This paper explores the design and evaluation of interfaces grounded in the sensemaking framework to support non-experts in auditing gender bias in image captioning. In a between-subjects study, 60 participants audited an image captioning model using one of three interface conditions: a Baseline interface, a Masking Tool for image manipulation, or a Filtering Tool for organizing captions. Our findings show that interface design shaped what participants noticed, how they interpreted model behavior, and supported their hypotheses. The Image Masking Tool enabled fine-grained testing of visual cues and context, while the Text Filtering Tool revealed broader asymmetries in gendered language. We argue that incorporating sensemaking into auditing practices can advance accountability and transparency in machine learning systems.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessSensemaking in User-Driven Algorithm Auditing: A Case Study on Gender Bias in an Image Captioning Model
Non-experts increasingly engage in user-driven algorithm auditing, interacting directly with AI systems to probe, document, and reflect on biased behavior. Yet, auditing remains challenging due to model opacity and limited support for navigating and interpreting outputs. This paper explores the design and evaluation of interfaces grounded in the sensemaking framework to support non-experts in auditing gender bias in image captioning. In a between-subjects study, 60 participants audited an image captioning model using one of three interface conditions: a Baseline interface, a Masking Tool for image manipulation, or a Filtering Tool for organizing captions. Our findings show that interface design shaped what participants noticed, how they interpreted model behavior, and supported their hypotheses. The Image Masking Tool enabled fine-grained testing of visual cues and context, while the Text Filtering Tool revealed broader asymmetries in gendered language. We argue that incorporating sensemaking into auditing practices can advance accountability and transparency in machine learning systems.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Artists on a Decade of AI Evolution: An Interview Study of Affordances, Culture, and Artistic Practice with Machine Learning
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessArtists on a Decade of AI Evolution: An Interview Study of Affordances, Culture, and Artistic Practice with Machine Learning
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Designing Movement Generation Models in Collaboration With Voguing And Dancehall Dancers
Recent advances in Artificial Intelligence have enabled powerful generative models, yet few are tailored to dancers’ practices. We present a long-term collaboration with a Voguing and Dancehall collective to design movement generation models trained on their repertoire. Our initial study with the dancers revealed that, despite limited physical realism, the generated movements inspired them. Iterative development led to Korai, an interactive tool for monitoring training, visualizing motion data, and prompting generation, which improved output quality. A subsequent structured observation study compared three model variants with high, medium, and low fidelity to the original dataset’s style. Results show that dancers favored either highly faithful or highly unfaithful outputs, rejecting medium fidelity as neither authentic to their style nor creatively stimulating. Our findings highlight how direct collaboration with dancers not only informs model design but also deepens understanding of AI’s role in supporting creative movement practices.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Open AccessDesigning Movement Generation Models in Collaboration With Voguing And Dancehall Dancers
Recent advances in Artificial Intelligence have enabled powerful generative models, yet few are tailored to dancers’ practices. We present a long-term collaboration with a Voguing and Dancehall collective to design movement generation models trained on their repertoire. Our initial study with the dancers revealed that, despite limited physical realism, the generated movements inspired them. Iterative development led to Korai, an interactive tool for monitoring training, visualizing motion data, and prompting generation, which improved output quality. A subsequent structured observation study compared three model variants with high, medium, and low fidelity to the original dataset’s style. Results show that dancers favored either highly faithful or highly unfaithful outputs, rejecting medium fidelity as neither authentic to their style nor creatively stimulating. Our findings highlight how direct collaboration with dancers not only informs model design but also deepens understanding of AI’s role in supporting creative movement practices.
- Open Access
- 28 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 96-101
Exploring people’s testing strategies in ML-based image classification
- 28 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 96-101
Open AccessExploring people’s testing strategies in ML-based image classification
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Generative AI in Documentary Photography: Exploring Opportunities and Challenges for Visual Storytelling
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessGenerative AI in Documentary Photography: Exploring Opportunities and Challenges for Visual Storytelling
- Open Access
- 6 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 31 (6) , 1-21
Prototyping with Uncertainties: Data, Algorithms, and Research through Design
Seen both as a resource and an obstacle to clarity, uncertainty is a concept that permeates many areas of design. As the concept gains prominence in Human-Computer Interaction (HCI), this special issue specifically explores the interplay between uncertainty and prototyping in Research through Design (RtD). We first outline three histories of uncertainty in design, in relation to its philosophical significance, its role in statistical and algorithmic processes, and its importance in prototyping. The convergence of these aspects is crucial as design evolves toward more agentive and entangled systems, introducing challenges such as Design as a Probabilistic Outcome. We then investigate the design spaces for engaging with “being uncertain” that emerge from the papers: from nuancing the relationship between designers and quantitative data to blurring the line between humans, fungi, and algorithms. Finally, we illuminate some preliminary threads for how RtD can navigate and engage with these shifting technological and design landscapes thoughtfully.
- 6 December 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 31 (6) , 1-21
Open AccessPrototyping with Uncertainties: Data, Algorithms, and Research through Design
Seen both as a resource and an obstacle to clarity, uncertainty is a concept that permeates many areas of design. As the concept gains prominence in Human-Computer Interaction (HCI), this special issue specifically explores the interplay between uncertainty and prototyping in Research through Design (RtD). We first outline three histories of uncertainty in design, in relation to its philosophical significance, its role in statistical and algorithmic processes, and its importance in prototyping. The convergence of these aspects is crucial as design evolves toward more agentive and entangled systems, introducing challenges such as Design as a Probabilistic Outcome. We then investigate the design spaces for engaging with “being uncertain” that emerge from the papers: from nuancing the relationship between designers and quantitative data to blurring the line between humans, fungi, and algorithms. Finally, we illuminate some preliminary threads for how RtD can navigate and engage with these shifting technological and design landscapes thoughtfully.