The Student Challenge aims to foster new and nascent design ideas centered around a specific challenge of relevance to the UbiComp/ISWC community this year. It encourages creative, impactful, and technically grounded student projects that connect AI with sensing and ubiquitous computing.

AI Agents and Foundation Models for Ubiquitous Sensing and Computing

Recent advances in AI have rapidly transformed how we interact with technology and interpret data. Beyond large language models, emerging AI agents and foundation models can reason over multimodal inputs, plan actions, coordinate tools, and interact with users and environments in more adaptive ways. These capabilities open up exciting opportunities for wearable, personal, and pervasive systems that rely on sensor data, context understanding, and timely assistance.

In this year’s UbiComp/ISWC Student Challenge, we invite teams of students from diverse academic backgrounds to unleash their creativity and develop innovative approaches that leverage AI agents, foundation models, or related generative AI techniques in combination with sensing datasets to create novel ubiquitous computing applications.

As part of the challenge, you can utilize any available open datasets, but we strongly encourage you to explore the recommended data sources on this page as a starting point. This challenge offers a unique platform to ideate, innovate, and showcase your ideas and creations to the UbiComp/ISWC conference attendees.

This year, we specifically invite participants to create innovative solutions that employ AI agents and/or foundation models to analyze sensing data, reason about context, coordinate actions, or provide meaningful, context-aware ubiquitous applications or services. Proposals should consider ethical issues arising in the proposed solution and describe how they can be addressed.

The UbiComp/ISWC Student Challenge presents a remarkable opportunity for you to showcase your work and creativity to leaders in the field and transform your innovative ideas into tangible reality. We will review and evaluate the proposed ideas considering Innovation, Creativity, Technical Implementation, and Ethical and Social Impact as the main criteria. Please note that selected proposals should be presented in person at the conference. The live presentation will also be part of the evaluation criteria.

Awards

Based on the evaluations from the panel of reviewers and judges, we will present three categories of awards, each accompanied by an award certificate:

• Best Student Challenge Award: For the individual/team that demonstrates excellence across all criteria.
• Most Creative Student Challenge Award: For the team that presents the most innovative and original approach to using AI agents, foundation models, or generative AI with sensing data.
• People’s Choice Student Challenge Award: Determined by audience votes during the conference demo session.

Summary of Key Dates

• June 15, 2026: Register your idea proposal abstract (max 1 A4 page) and register your team using this Google form.
• June 25, 2026: Initial feedback to the proposal abstract.
• July 10, 2026: Submit a short paper describing your proposal’s key challenges and design approach. The short paper should contain design outputs (e.g. wireframes, storyboards etc.), and any implementation details or results, if available (max 4 pages using the ACM SIGCHI 2-column conference template).
• July 15, 2026: Acceptance notification of the paper.
• July 25, 2026: Camera Ready Submission.
• September 26, 2026: Submit a video demo (max 3 minutes), and code repository of your solution (optional).
• October 5, 2026: Complete the development and presentation of the solution.
• October 11-15, 2026: Participate in the conference and present a poster and live demonstration of your project.

Publication

Accepted papers will be published in the conference adjunct proceedings, available through the ACM Digital Library.

Data Sources for the Challenge

We encourage participants to explore and utilize any publicly available sensing datasets that align with their project ideas. Some suggested datasets include:

• StudentLife Dataset: Contains smartphone sensing data that monitors student activities, behaviors, and states.
• GLOBEM Dataset: A multi-modal sensing dataset focusing on behavioral and emotional measurements.
• In-Gauge & En-Gage Datasets: Heterogeneous sensing and wearable data focused on student behaviour, engagement, emotion, comfort indoors and contextual interactions.
• PAMAP2 Dataset: Contains wearable sensor data for monitoring physical activities such as walking, running, and household tasks.
• ExtraSensory Dataset: Captures real-world context using smartphone and smartwatch sensors, including motion, audio, GPS, and user-reported activities.
• DOMINO Dataset: Provides multimodal sensor data from naturalistic home environments, enabling activity recognition and human-object interaction studies.
• DSADS Dataset: Records motion data from multiple body-worn IMUs during daily and sports activities.
• KU-HAR Dataset: Includes smartphone-based accelerometer and gyroscope data for human activity recognition.
• ARAS Dataset: Contains sensor data from smart home environments with multiple residents.

You are not limited to these datasets and are welcome to use any open-source sensing datasets that suit your project needs. If you cannot find the data you need, it is acceptable to create synthetic data, collect your own, or use simulated environments to generate data. The key requirement is that your project demonstrates innovative applications of AI agents, foundation models, or generative AI in interpreting, analyzing, interacting with, or acting upon sensing data.

Submission Details

Final submissions should follow the conference format requirements:

• Maximum 4 pages excluding references
• Anonymized for blind review
• Prepared using the conference proceedings template
• Reviewed by at least two technical program committee members or chairs
• Accepted papers published in the conference adjunct proceedings

Competition Format

Idea Submission

All participating teams must submit their ideas using the designated registration form.

Your submission should include:

1. Names and contact information for team members
2. Topic/title of your idea
3. Description of your idea (max 1 page), including the dataset you intend to use and/or the functionalities of your software solution
4. Optional links to supporting materials such as images, videos, slides, or other multimedia resources

Review and Notification

The Student Challenge chairs will review the idea submissions and notify teams whether they have been accepted to the next round.

Demo Development

After acceptance, student teams may reach out to the organizers for support, advice, or mentoring during the development phase. Depending on the number of submissions and organizer availability, a technical kick-off meeting may also be organized.

Project Submission

Each participating team should submit the following materials:

• Short paper (max 4 pages): The paper should include the motivation, background, and design/technical description of the solution, as well as a minimum number of references as specified by the conference website. The short paper should clearly describe how the technology benefits users, including possible malicious uses beyond privacy concerns. Design approaches should consider ways to mitigate ethical, social, and security implications.
• Video demo (max 3 minutes): The video should showcase a complete use case of the technology and incorporate storytelling elements to provide context and enhance understanding.
• Code repository (optional): While not mandatory, teams are encouraged to open-source their code to support transparency and collaboration. If included, the repository should provide clear installation and usage instructions.

Conference Presentation

Teams will showcase their demos at the conference. Alongside the demo presentation, teams should prepare a poster that concisely summarizes the idea, design, and implementation.

Evaluations will be conducted by a jury and the audience, with the chance to win awards.

Project Ideas

Here are some ideas to inspire your submissions focused on AI agents, foundation models, and sensing data:

• Context-Aware Ubiquitous Applications
  • Develop systems that use AI to understand sensor patterns, reason about context, and respond with adaptive assistance.
  • Create applications where foundation models interpret wearable sensor data to provide personalized insights or recommendations.
  • Design interactive systems that allow users to query, summarize, and act on their own sensing data history.
• AI for Sensor Data Interpretation
  • Build solutions that translate raw sensor data into meaningful narratives, explanations, or actionable plans.
  • Develop systems that detect anomalies in sensor streams and generate human-readable explanations or recommended next steps.
  • Create applications that combine multiple sensor streams and use AI systems to provide holistic interpretations of situations or environments.
• Predictive and Proactive Sensing with AI
  • Design systems that use historical sensor data and AI models to predict future states, needs, or risks.
  • Create applications that anticipate user actions based on sensing patterns and proactively provide assistance.
  • Develop tools that forecast contextual changes and suggest preemptive actions through natural language interaction.
• Privacy-Preserving AI for Sensing
  • Develop frameworks for using AI agents or foundation models with sensing data while protecting user privacy.
  • Create systems that allow users to query their sensor data without exposing sensitive information.
  • Design architectures where AI systems can provide insights without requiring access to raw sensor data.
• Behavioral Understanding from Longitudinal Sensing
  • Build applications that interpret long-term patterns in sensing data to reveal behavioral trends.
  • Develop systems that identify correlations across different sensing modalities.
  • Create tools that turn sensing data into personalized behavioral recommendations.
• AI for Large-Scale and Multimodal Sensor Data
  • Design workflows to navigate and integrate multimodal sensor data from different datasets.
  • Create tools that enrich sensor data with external knowledge to improve interpretation.
  • Fuse sensor datasets and extract compact representations for personalized downstream modeling.
• On-Device and Edge AI for Personal and Wearable Devices
  • Distill or adapt models into smaller context-aware systems tailored for specific situations.
  • Develop collaborative system infrastructure across multiple devices to run open-source models.
  • Develop edge-oriented architectures for running compact models or agent components near the user.
• AI for Sensor Programming and Automation
  • Develop tools that leverage AI to analyze sensor specifications and environmental factors, automatically generating initialization, calibration, or orchestration logic.
  • Develop dynamic software systems that adapt sensor behavior based on real-world feedback.
  • Develop programming solutions that translate sensor data across modalities, such as converting camera input into IMU-like representations for situational awareness.

Competition Rules, Details, and Suggestions

• Team Size and Composition: Teams should be composed of 2 to 5 students. Students do not need to be from the same institution and may come from different educational backgrounds, including Bachelor’s, Master’s, and PhD programs.
• Judging Criteria: Projects will be judged based on:
  • Innovation and Creativity
  • Technical Implementation
  • Social Impact
  • Ethical awareness and responsible design considerations
• Registration Requirement: Teams must register for the contest and submit their idea through the designated form. If accepted, at least one team member must register for the conference and attend in person.