{"id":4717,"date":"2024-03-29T22:26:09","date_gmt":"2024-03-29T22:26:09","guid":{"rendered":"https:\/\/xaiworldconference.com\/2024\/?post_type=mp-event&p=4717"},"modified":"2026-05-17T11:14:48","modified_gmt":"2026-05-17T11:14:48","slug":"late-breaking-work-demos-coffee-break-2","status":"publish","type":"mp-event","link":"https:\/\/xaiworldconference.com\/2026\/timetable\/event\/late-breaking-work-demos-coffee-break-2\/","title":{"rendered":"Late-breaking work + Demos + DC (poster session coffee break morning)"},"content":{"rendered":"\n

Late-breaking work<\/strong><\/p>\n\n\n\n

Francesco Leofante, Daniel Neider and Mustafa Yalciner<\/td>Evaluating Counterfactual Explanation Methods on Incomplete
Inputs<\/td><\/tr>
Samar Heydari, Jawher Said, Galip \u00dcmit Yolcu, Evgenii
Kortukov, Elena Golimblevskaia, Evgenios Vlachos, Vasileios
Mygdalis, Ioannis Pitas, Sebastian Lapuschkin and Leila
Arras<\/td>		Concept-based explanations of Segmentation and Detection
models in Natural Disaster Management<\/td><\/tr>
Luis Paulo Guedes, Mariane Petraglia and Julio Cesar Torres<\/td>Interpretability-Informed Curriculum Learning for Blind
Estimation of Room Acoustic Parameters with a Vision
Transformer<\/td><\/tr>
Takafumi Nakanishi<\/td>NS-AIME: Rule-Guided Re-Constraint of Approximate Inverse
Explanations<\/td><\/tr>
Pinar Karadayi Atas and Luca Longo<\/td>CAX-Gate: a Context-Aware Explainability Fusion
Architecture for Dynamical Adjustment of LIME-to-SHAP
attributions ratio with application in Colonoscopy<\/td><\/tr>
Ricardo Knauer, Andre Beinrucker and Erik Rodner<\/td>ConceptTracer: Interactive Analysis of Concept Saliency and
Selectivity in Neural Representations<\/td><\/tr>
Lucas Rizzo and Luca Longo<\/td>Exploring the accuracy-size trade-off in extended
argumentative decision graphs using SHAP or LIME feature
selection<\/td><\/tr>
Golnoosh Babaei, Marco Brandirali and Paolo Giudici<\/td>SAFE AI platform: A Platform for Continuous Evaluation of
Accuracy, Fairness, Explainability and Robustness in
Machine Learning Systems<\/td><\/tr>
Thi Hoang Anh Tran, Emiel Caron and Hans Weigand<\/td>Investigating inductive bias in LLMs – A case study in
creditworthiness assessment<\/td><\/tr>
Aleksander Krasowski, Ren\u00e9 P. Klausen, Aycan Celik,
Sebastian Lapuschkin, Wojciech Samek and Jonas Naujoks<\/td>		Building Trust in PINNs: Error Estimation through Finite
Difference Methods<\/td><\/tr>
Risal Shefin, Debashis Gupta, Murtadha Alsayegh and Sarra
Alqahtani<\/td>		When One Agent Reshapes Another: Cross-Hessian
Interpretation of Local Coupling in MARL<\/td><\/tr>
Saheed Faremi, Andrea Visentin and Luca Longo<\/td>Interpretable EEG Microstate Discovery via Variational Deep
Embedding: A Systematic Architecture Search with
Multi-Quadrant Evaluation<\/td><\/tr>
Pablo P\u00e9rez-L\u00e1zaro, Roc\u00edo Aznar-Gimeno and Rafael
del-Hoyo-Alonso<\/td>		Delayed Convergence and Emergent CoT Reliance in RL-Tuned
Language Models<\/td><\/tr>
Filipe Bernardi, Daniel Rodrigues, Rute Almeida, Vinicius
Lima, Isabela Guerche, Julio Souza, Ricardo Correia, Luis
Concei\u00e7\u00e3o, Goreti Marreiros and Alberto Freitas<\/td>		Calibrating Clinician Trust in Explainable AI Summarization
for Obstetrics: A Sociotechnical Design Study of the MedGPT
Portugal Use Case<\/td><\/tr>
Vasily Kolesnikov, Damiano Verda, Nicol\u00f2 Pinna, Danilo
Franco and Paolo Giudici<\/td>		Evaluating Logic Learning Machine model with SAFE-AI Metrics<\/td><\/tr>
Barbara Tarantino and Paolo Giudici<\/td>ISAAC: Intervention-Based Structural Auditing of Deep
Models for Transcription Factor Binding<\/td><\/tr>
Oleksandr Davydko, Volodymyr Pavlov and Luca Longo<\/td>Multi-metric Evaluation of the Statistical Radiomic Feature
Activation Map method for Explainable Radiomic Models<\/td><\/tr>
Iain Swift, Jinghua Ye and Ruairi O’Reilly<\/td>Quantifying Cross-Modal Interactions in Multimodal Glioma
Survival Prediction via InterSHAP: Evidence for Additive
Signal Integration<\/td><\/tr>
Raj Kiran Gupta Katakam<\/td>AGOP as Explanation: From Feature Learning to Per-Sample
Attribution in Image Classifiers<\/td><\/tr>
Jean-Marc Boutay, Guido Bologna, Damian Boquete, Deniz
K\u00f6pr\u00fcl\u00fc and Ludovic Pfeiffer<\/td>		Patch-Masking Approach to Explain CNNs and Vision
Transformers through Class-Specific Impacts<\/td><\/tr>
Tommaso Colafiglio, Angela Lombardi, Paolo Sorino, Domenico
Lof\u00f9 and Tommaso Di Noia<\/td>		Explainable Emotion Recognition with EEG Wearable Devices<\/td><\/tr>
Andr\u00e9 Zanon and Derek Bridge<\/td>Explanation-Driven Carousels for Two-Dimensional
Recommendation Interfaces<\/td><\/tr>
Paul Darm, Cem Alpturk, Kenneth Ulrich, William Duncan, Ali
Anwar and Annalisa Riccardi<\/td>		Explaining Process Control Optimisation Recommendations via
GradientSHAP and Implicit Differentiation<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

Demos<\/strong><\/p>\n\n\n\n

Reinaldo Rosa, Andressa Ferreira, Salatiel Jord\u00e3o, Carlos Falandes, Mariana Rubet, Andr\u00e9 Martinon, Stephan Stephany, Francisco Fernandes and Juan Valdivia<\/td>Explainable AI for Operational Space Weather Forecasting: An Interpretable Prototype for the EMBRACE-INPE Monitoring Network<\/td><\/tr>
Tuwe L\u00f6fstr\u00f6m and Helena L\u00f6fstr\u00f6m<\/td>Calibrated Explanations – Trustworthy uncertainty for every prediction and explanation<\/td><\/tr>
Adelia Manafov, Artem Mozharov, Khawla Elhadri, Ramona Simon, Jan Gohe, Max Bl\u00fcmer, Ben Williges, J\u00f6rg Schl\u00f6tterer, Diana Arweiler-Harbeck, Benedikt H\u00f6ing and Christin Seifert<\/td>XTAB-CDS: A lightweight framework for explainable clinical decision support on tabular data<\/td><\/tr>
Henrique Margotte, Bruno Meyer, Carmem Hara, Aurora Pozo and Wagner Zola<\/td>GPUTextSHAP: a GPU-Accelerated Permutation SHAP for Textual Data<\/td><\/tr>
Oleksii Kalashnikov, Jonas Amling, Christian Dormagen, Andreas Fischer, Stephan Scheele and Ute Schmid<\/td>Grounding LLM Explanations for Process Mining via Agentic Function Calling<\/td><\/tr>
Seunghyun Lee<\/td>Suppressive Dropout: A Demonstration of Explainable Channel-Selective Regularization for Preserving Rare Features<\/td><\/tr>
Himanshu Joshi, Shivani Shukla, Sunita Kumari and Manas Joshi<\/td>SafeAlign: Demonstrating Safety Alignment Governance and Security (SAGS) for Explainable Multi-Agent AI<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

Doctoral Consortium<\/strong><\/p>\n\n\n\n

Maurice Pape<\/td>User Arousal in XAI Usage<\/td><\/tr>
Kudzai Sauka<\/td>Human-Centred Explainable Conversational AI: Explainability, Persona Adaptation, and Entrepreneurial Agency<\/td><\/tr>
Daniel da Silva Costa<\/td>An Approach to Selecting the Best Explainability Method for CNNs Based on Distance Metrics and Human Perception<\/td><\/tr>
Mingxing Zhang<\/td>Progressive and Interpretable Explanations for Machine Learning Models on Spectroscopy Data<\/td><\/tr>
Liziane Santos Soares<\/td>A Comprehensive Investigation of the Impact of Locality on the Explainability of Automatic Text Classification<\/td><\/tr>
Saheed Faremi<\/td>Explainable Disentangled Representation Learning of Recurring Brain Activation Patterns via Variational Autoencoders<\/td><\/tr>
Korbinian Franz Rudolf<\/td>Condensed Dataset Representations via Latent Prototypical Features<\/td><\/tr>
Cristian dos Anjos<\/td>Explainability-Guided Active Data Acquisition for Classification<\/td><\/tr>
Francesco Musicco.<\/td>Multi-Agent Evaluation of XAI for Human-AI Trust and Cooperative Adaptation<\/td><\/tr>
Marco Aspromonte<\/td>Towards Structural Explainability for Reliable and Governable Large Language Models<\/td><\/tr><\/tbody><\/table><\/figure>\n","protected":false},"excerpt":{"rendered":"

Late-breaking work Francesco Leofante, Daniel Neider and Mustafa Yalciner Evaluating Counterfactual Explanation Methods on IncompleteInputs Samar Heydari, Jawher Said, Galip \u00dcmit Yolcu, EvgeniiKortukov, Elena Golimblevskaia, Evgenios Vlachos, VasileiosMygdalis, Ioannis Pitas, Sebastian Lapuschkin and LeilaArras Concept-based explanations of Segmentation and Detectionmodels in Natural Disaster Management Luis Paulo Guedes, Mariane Petraglia and Julio Cesar Torres Interpretability-Informed Curriculum … <\/p>\n","protected":false},"author":2,"featured_media":0,"menu_order":0,"template":"","mp-event_category":[64],"mp-event_tag":[],"class_list":["post-4717","mp-event","type-mp-event","status-publish","hentry","mp-event_category-18th-of-july","mp-event-item"],"_links":{"self":[{"href":"https:\/\/xaiworldconference.com\/2026\/wp-json\/wp\/v2\/mp-event\/4717","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/xaiworldconference.com\/2026\/wp-json\/wp\/v2\/mp-event"}],"about":[{"href":"https:\/\/xaiworldconference.com\/2026\/wp-json\/wp\/v2\/types\/mp-event"}],"author":[{"embeddable":true,"href":"https:\/\/xaiworldconference.com\/2026\/wp-json\/wp\/v2\/users\/2"}],"wp:attachment":[{"href":"https:\/\/xaiworldconference.com\/2026\/wp-json\/wp\/v2\/media?parent=4717"}],"wp:term":[{"taxonomy":"mp-event_category","embeddable":true,"href":"https:\/\/xaiworldconference.com\/2026\/wp-json\/wp\/v2\/mp-event_category?post=4717"},{"taxonomy":"mp-event_tag","embeddable":true,"href":"https:\/\/xaiworldconference.com\/2026\/wp-json\/wp\/v2\/mp-event_tag?post=4717"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}