Conference Program

Workshops, Tutorials, and Doctoral Consortium - Monday March 24

11:00 - 11:30 AM, Coffee Break | 01:00-02:30 PM, Launch break | 04:00 - 04:30 PM, Coffee Break | 06:00, Closing

Room	Morning	Afternoon
T4	HAI-GEN 2025	HAI-GEN 2025
T1a	HealthIUI	AXAI
T1b	MIND	MIND
T1c	BEHAVE AI	BEHAVE AI
T3a	SOCIALIZE	STEP-HAI
T3b	Doct. Cons.	Doct. Cons.
T8	DECI	DECI

This schedule contains paper slots with 10 mins presentation and 5 mins for questions. The sessions within the same cells (e.g. S1 [new line] S2) indicate parallel sessions.

Main Conference (March 25-27)

6:00 PM, Tuesday 25 – Welcome Cocktail
7:30 PM, Wednesday 26 – Social Dinner

Time	Tuesday March 25th	Wednesday March 26th	Thursday March 27th
8:30 AM - 8:45 AM	Registration
8:45 AM - 9:00 AM	Welcome
9:00 AM - 10:00 AM	Chair: Kaisa Väänänen Keynote #1 Albrecht Schmidt	Chair: Fabio Paternò Impact paper : Jerry Fails Panel: M. Burnett, E. Churcill, K. Gajos	Chair: Toby Li Keynote #2 Q. Vera Liao
10:05 AM - 11:05 AM	T1 AR/VR (4) T3 TiiS papers (4)	Coffee break + Posters and Demos	T1 Democratisation of AI (3) T3 User adaptation (4)
11:05 AM - 11:25 AM	Coffee break	Coffee break + Posters and Demos	Coffee break
11:25 AM - 12:55 PM	T1 Interactive ML (6) T3 Multimodal AI (4)	T1 Generative models (5) T3 User studies (5 + 1 TiiS)	T1 Collaboration and interaction (4) T3 Recommendation (5)
12:55 PM - 2:25 PM	Lunch
2:25 PM - 4:25 PM	T1 XAI methods (7) T3 Knowledge-based approaches (7)	T1 LLM 1 (7) T3 XAI methods 2 (7)	T1 LLM 2 (6+1) T3 Video Presentation (12)
4:25 PM - 4:45 PM	Coffee break
4:45 PM - 5:45 PM	T1 Visualisation (4) T3 User modeling (4)	Posters and Demos	Town hall and Closing
6:00 PM	Welcome Cocktails
7:30 PM		Social Dinner

Session List

• AR/VR
  • GlideRX: Enhancing Situation Awareness for Collision Prevention in Glider Flight through Extended Reality
  • A picture is worth a thousand words? Investigating the Impact of Image Aids in AR on Memory Recall for Everyday Tasks
  • KHAIT: K-9 Handler Artificial Intelligence Teaming for Collaborative Sensemaking
  • Video2MR: Automatically Generating Mixed Reality 3D Instructions by Augmenting Extracted Motion from 2D Videos
• TiiS Papers
  • "I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming
  • "It would work for me too": How Online Communities Shape Software Developers’ Trust in AI-Powered Code Generation Tools
  • Ajna: A Wearable Shared Perception System for Extreme Sensemaking
  • 🌳-generAItor: Tree-in-the-loop Text Generation for Language Model Explainability and Adaptation
• Democratisation of AI
  • DeepFlow: A Flow-Based Visual Programming Tool for Deep Learning Development
  • More than Marketing? On the Information Value of AI Benchmarks for Practitioners
  • AiModerator: A Co-Pilot for Hyper-Contextualization in Political Debate Video
• User Adaptation
  • An Exploratory Study on How AI Awareness Impacts Human-AI Design Collaboration
  • Controlling AI Agent Participation in Group Conversations: A Human-Centered Approach
  • ShareFlows: Seamless knowledge capture and proactive push for efficient teacher workflows in higher education
  • Under the Hood of Carousels: Investigating User Engagement and Navigation Effort in Multi-list Recommender Systems
• Interactive ML
  • Cluster-Based Approach for Visual Anomaly Detection in Multivariate Welding Process Data Supported by User Guidance
  • Interoceptive Objects: opportunistic harnessing of internal signals for state self-monitoring
  • HEPHA: A Mixed-Initiative Image Labeling Tool for Specialized Domains
  • Empowering Medical Data Labeling for Non-Experts with DANNY: Enhancing Accuracy and Mitigating Over-Reliance on AI
  • Towards Trustable Intelligent Clinical Decision Support Systems: A User Study with Ophthalmologists
  • User-Guided Correction of Reconstruction Errors in Structure-from-Motion
• Multimodal AI
  • ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine Conversations
  • Text-to-Image Generation for Vocabulary Learning Using the Keyword Method
  • TellTime: An AI-Augmented Calendar with a Voice Interface for Collecting Time-Use Data
  • MemPal: Leveraging Multimodal AI and LLMs for Voice-Activated Object Retrieval in Homes of Older Adults
• Generative Models
  • Diffuse Your Data Blues: Augmenting Low-Resource Datasets via User-Assisted Diffusion
  • Interactive High-Quality Skin Lesion Generation using Diffusion Models for VR-based Dermatological Education
  • Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models
  • Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learning
  • Simulating Cooperative Prosocial Behavior with Multi-Agent LLMs: Evidence and Mechanisms for AI Agents to Inform Policy Decisions
• User Studies
  • Slip Through the Chat: Subtle Injection of False Information in LLM Chatbot Conversation Increases False Memory Formation
  • TSConnect: An Enhanced MOOC Platform for Bridging Communication Gaps Between Instructors and Students in Light of the Curse of Knowledge
  • ArtInsight: Enabling AI-Powered Artwork Engagement for Mixed Visual-Ability Families
  • Evaluating the Impact of Automated Hints in a 3D Educational Escape Game: A Comparative Study of Accessibility and Computer Science Versions
  • Counselor-AI Collaborative Transcription and Editing System for Child Counseling Analysis
  • Measuring User Experience Inclusivity in Human-AI Interaction via Five User Problem-Solving Styles
• Collaboration and Interaction
  • One Does Not Simply Meme Alone: Evaluating Co-Creativity Between LLMs and Humans in the Generation of Humor
  • MaGEL: A Soft, Transparent Input Device Enabling Deformation Gesture Recognition
  • 3D Touch Force Estimation from Capacitive Images
  • Real-Time Full-body Interaction with AI Dance Models: Responsiveness to Contemporary Dance
• Recommendation
  • FretMate: ChatGPT-Powered Adaptive Guitar Learning Assistant
  • Prefer2SD: A Human-in-the-Loop Approach to Balancing Similarity and Diversity in In-Game Friend Recommendations
  • Orbit: A Framework for Designing and Evaluating Multi-objective Rankers
  • Words as Bridges: Exploring Computational Support for Cross-Disciplinary Translation Work
  • Can LLMs Recommend More Responsible Prompts?
• XAI Methods (1/2)
  • SkinGEN: an Explainable Dermatology Diagnosis-to-Generation Framework with Interactive Vision-Language Models
  • Robust Relatable Explanations of Machine Learning with Disentangled Cue-specific Saliency
  • From Oracular to Judicial: enhancing clinical decision making through contrasting explanations and a novel interaction protocol
  • Less or More: Towards Glanceable Explanations for LLM Recommendations Using Ultra-Small Devices
  • The Influence of Curiosity Traits and On-Demand Explanations in AI-Assisted Decision-Making
  • Building Appropriate Mental Models: What Users Know and Want to Know about an Agentic AI Chatbot
  • Counterfactual Explanations May Not Be the Best Algorithmic Recourse Approach
• Knowledge-based Approaches
  • Dynamik: Syntactically-Driven Dynamic Font Sizing for Emphasis of Key Information
  • CGAT-Net: Context-Aware Graph Attention Transformer Network for Scene Sketch Recognition
  • Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotation
  • To Guide Or To Disturb- -How To Teach Dexterous Skills Using AI?
  • A Design Space for Intelligent Dialogue Augmentation
  • DreamDirector: Designing a Generative AI System to Aid Therapists in Treating Clients’ Nightmares
  • Technologies Supporting Self-Reflection on Social Interactions: A Systematic Review
• LLM 1
  • Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks
  • Advancing Affective Intelligence in Virtual Agents Using Affect Control Theory
  • Lotus: Creating Short Videos From Long Videos With Abstractive and Extractive Summarization
  • EditIQ: Automated Cinematic Editing of Static Wide-Angle Videos via Dialogue Interpretation and Saliency Cues
  • A Framework for Efficient Development and Debugging of Role-Playing Agents with Large Language Models
  • Mental Models of Generative AI Chatbot Ecosystem
  • From Interaction to Impact: Towards Safer AI Agent Through Understanding and Evaluating Mobile UI Operation Impacts
• XAI Methods (2/2)
  • Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant
  • Personalising AI assistance based on overreliance rate in AI-assisted decision making
  • How Dynamic vs. Static Presentation Shapes User Perception and Emotional Connection to Text-Based AI
  • Benefits of Machine Learning Explanations: Improved Learning in an AI-assisted Sequence Prediction Task
  • VibE: A Visual Analytics Workflow for Semantic Error Analysis of CVML Models at Subgroup Level
  • Evaluating the Impact of AI-Generated Visual Explanations on Decision-Making for Image Matching
  • Will Health Experts Adopt a Clinical Decision Support System for Game-Based Digital Biomarkers? Investigating the Impact of Different Explanations on Perceived Ease-of-Use, Perceived Usefulness, and Trust
• LLM 2
  • CLEAR: Towards Contextual LLM-Empowered Privacy Policy Analysis and Risk Generation for Large Language Model Applications
  • “You Always Get an Answer”: Analyzing Users’ Interaction with AI-Generated Personas Given Unanswerable Questions and Risk of Hallucination
  • PromptMap: An Alternative Interaction Style for AI-Based Image Generation
  • SimTube: Simulating Audience Feedback on Videos using Generative AI and User Personas
  • Enhancing Visitor Engagement in Interactive Art Exhibitions with Visual-Enhanced Conversational Agents
  • DancingBoard: Streamlining the Creation of Motion Comics to Enhance Narratives
  • A Prompt Chaining Framework for Long-Term Recall in LLM-Powered Intelligent Assistant
• Video Presentation
  • Enhancing Immersive Sensemaking with Gaze-Driven Recommendation Cues
  • A Design Space of Behavior Change Interventions for Responsible Data Science
  • Designing LLM-simulated Immersive Spaces to Enhance Autistic Children's Social Affordances Understanding in Traffic Settings
  • VideoMix: Aggregating How-To Videos for Task-Oriented Learning
  • A Dynamic Bayesian Network Based Framework for Multimodal Context-Aware Interactions
  • SAE: A Multimodal Sentiment Analysis Large Language Model
  • Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks
  • NoTeeline: Supporting Real-Time, Personalized Notetaking with LLM-Enhanced Micronotes
  • Can VTA Empower Learners to Ask Critical Questions?
  • Help Wanted – or Not: Bridging the Empathy Gap between Wheelchair Users and Passersby through AI-Mediated Communication with Politeness Strategies
  • Gensors: Authoring Personalized Visual Sensors with Multimodal Foundation Models and Reasoning
  • Authoring LLM-Based Assistance for Real-World Contexts and Tasks
  • Conversational Explanations: Discussing Explainable AI with Non-AI Experts
  • CoPrompter: User-Centric Evaluation of LM Instruction Alignment for Improved Prompt Engineering
• Visualisation
  • StratIncon Detector: Analyzing Strategy Inconsistencies Between Real-Time Strategy and Preferred Professional Strategy in MOBA Esports
  • Guidance Source Matters: How Guidance from AI, Expert, or a Group of Analysts Impacts Visual Data Preparation and Analysis
  • Pluto: Authoring Semantically Aligned Text and Charts for Data-Driven Communication
  • Analyzing the Shifts in Users Data Focus in Exploratory Visual Analysis
• User Modeling
  • Crying Jaywalker! Notifying Take-Over-Requests and Critical Events in Operational Driving Domain of Autonomous Vehicles via Multimodal Interfaces
  • Redefining Affordance via Computational Rationality
  • The Effects of Customisation on the Usability of Visual Analytics Dashboards: the Good, the Bad, and the Ugly
  • Coalesce: An Accessible Mixed-Initiative System for Designing Community-Centric Questionnaires