Submission Deadline: June 15, 2025

The Student Challenge aims to foster new and nascent design ideas featuring around a specific challenge of relevance to the UbiComp/ISWC community this year.

LLM for Ubiquitous Sensing and Computing

Large Language Models (LLMs) have rapidly transformed how we interact with technology and interpret data. These powerful AI models offer unprecedented capabilities for understanding context, processing natural language queries, and generating insights from complex information sources including sensor data.  As LLMs evolve, seamless integration with wearable, personal, and pervasive systems becomes increasingly essential. 

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 LLMs 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 in 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 LLMs to analyze sensing data and 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 esteemed leaders in the field and transform your innovative ideas into tangible reality. This year, we will review and evaluate the proposed ideas, considering Innovation, Creativity, Technical Implementation, Ethical and Social Impact as the main criteria. Please note that the 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/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 LLMs with sensing data.
• People’s Choice Student Challenge Award: Determined by audience votes during the conference demo session.

Summary of Key Dates

• June 15, 2025: Register your idea proposal abstract (max 1 A4 page) and register your team using this Google form.
• June 25, 2025: Initial feedback to the proposal abstract. 
• July 10, 2025: 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, 2025: Acceptance notification of the paper. 
• July 25, 2025: Camera Ready Submission. 
• September 26, 2025: Submit a video demo (max 3 minutes), and code repository of your solution (optional). 
• October 5, 2025: Complete the development and presentation of the solution. 
• October 12-16, 2025: Participate in the conference and present a poster and live demonstration of your project.

Publication: Accepted papers will be published in the UbiComp/ISWC 2025 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 your 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 (IMUs and heart rate) for monitoring physical activities like 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 five IMUs on the body during daily and sports activities, supporting multisensor activity classification. 
• KU-HAR Dataset: Includes smartphone-based accelerometer and gyroscope data for recognizing 18 human activities performed by multiple subjects. 
• ARAS Dataset: Contains sensor data from smart home environments with multiple residents, used to recognize daily activities and model inter-person interactions. 

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’re looking for, it is perfectly 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 LLMs in interpreting, analyzing, or interacting with sensing data. 

Submission Details

Final Submission (Deadline: July 10, 2025)

The Student Challenge is now open for submissions via PCS system. Please ensure your proposals adhere to the guidelines provided on the Student Challenge website. Only teams whose proposals are accepted in the first round will be invited to submit a final paper for review. Submission Website: https://new.precisionconference.com/submissions (Society: SIGCHI → Conference Ubicomp/ISWC 2026 → Track: Ubicomp/ISWC 2025 Student Competition)

Submissions must adhere to formatting requirements: a maximum of 4 pages (excluding references), anonymized for blind review, and prepared using the UbiComp/ISWC 2025 Proceedings Template (https://www.ubicomp.org/ubicomp-iswc-2025/authors/formatting/). All submissions will be reviewed by at least two technical program committee members or Chairs. All accepted papers will be published in the UbiComp/ISWC 2025 Adjunct Proceedings.

Competition Format

Idea Submission (Deadline: June 15, 2025)

All participating teams must submit their ideas using this form. The team registration deadline is June 15, 2025. 

Your submission should include the following:

1. Names and contact information for your team members: Provide names, institution, and email address of 2-5 team members, and contact information for the team leader.
2. Topic/Title of your idea: Provide the general topic, or a specific title for the idea you want to develop in your challenge.
3. Description of your idea (max 1 page): Provide a summary of your idea, if you intend to use a reference dataset and how, and/or specific functionalities of your software solution
4. Link to supporting materials (Optional): Include links to any relevant supporting materials such as images, videos, PowerPoint presentations, or other multimedia resources.

Completion of registration form: Ensure that all the required fields on the registration form are filled out accurately, including contact information and any other necessary details.

Review and Notification (Deadline: June 25, 2025)

The student challenge chairs will review your idea submission and notify you by June 25 if your submission has been accepted in the first round.

Demo Development (June 25, 2025 to October 5, 2025)

The demo development phase starts after the notification of acceptance (June 25, 2025) and lasts until October 5, 2025.

Student teams can reach out to the SDC organisers for support, advice or mentoring during the development phase via email. Depending on the number of submissions and team member availability, we may also organise a technical kick-off meeting in July to assist with any queries about the challenge.

Project Submission (Multiple deadlines!)

Each participating team should submit the following materials:

• [July 10, 2025] Short paper (max 4 pages): The paper should include the motivation, background, and design / technical description of the solution, and include a minimum of 4 references. Please use the UbiComp/ISWC templates and guidelines to prepare the short paper. The short papers should provide a clear description of how the technology benefits users, including potential malicious uses beyond privacy concerns. Design approaches should consider approaches to mitigate possible ethical, social, and security implications. 
• [September 26, 2025] 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 of the submission. 
• [September 26, 2025] Code repository (Optional): While not mandatory, we encourage you to open-source your code, as it allows for greater transparency and collaboration. If you do, please include clear instructions for installation and usage to facilitate evaluation and replication of your solution. It is important to note that the quality of the code will not be a factor in the judging process, so feel free to share your code regardless of its current state

Conference Presentation

Teams will showcase their demos at UbiComp/ISWC 2025. Alongside the demo presentation, please prepare a poster that concisely summarizes your 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 LLMs with sensing data:

• LLM-Enhanced Context-Aware Ubiquitous Applications
  • Develop systems that use LLMs to understand and respond to complex sensor patterns that traditional algorithms might miss. 
  • Create applications where LLMs interpret wearable sensor data to provide personalized health insights or recommendations. 
  • Design conversational interfaces that allow users to query their own sensing data history with natural language questions.
• LLMs for Sensor Data Interpretation
  • Build solutions that use LLMs to translate raw sensor data into meaningful narratives about user activities or environments. 
  • Develop systems that can detect anomalies in sensor data streams and generate human-readable explanations. 
  • Create applications that combine multiple sensor streams and use LLMs to provide holistic interpretations of situations or environments.
• LLM-Powered Predictive Sensing
  • Design systems that use historical sensor data and LLMs to predict future states or needs of users.
  • Create applications that anticipate user actions based on patterns in sensing data and proactively provide assistance.
  • Develop tools that forecast environmental or contextual changes and suggest preemptive actions through natural language communication.
• Privacy-Preserving LLM Analysis
  • Develop frameworks for using LLMs with sensing data while protecting user privacy. 
  • Create systems that allow users to query their sensor data through LLMs without exposing sensitive information. 
  • Design architectures where LLMs can provide insights without requiring access to raw sensor data
• LLM-Driven Behavioral Understanding
  • Build applications that use LLMs to interpret long-term patterns in sensing data to reveal insights about behavioral trends. 
  • Develop systems that can identify correlations between different types of sensing data using LLMs’ pattern recognition capabilities. 
  • Create tools that translate sensing data into personalized behavioral recommendations delivered through natural language.
• LLM for Big Sensor Data
  • Design advanced prompts to navigate and integrate multimodal sensor data from different datasets for complex representations of human activity and context. 
  • Create tools to boost spatial and temporal characteristics of sensor data samples with LLM knowledge 
  • Fuse sensor datasets and extract compact representations for personalized model training. 
• On-device LLM for Personal and Wearable Devices
  • Distill LLMs into smaller, context-aware models tailored for specific situations 
  • Develop collaborative system infrastructure across multiple devices to run open-source LLMs. 
  • Develop cloudlet and edge-oriented architectures for running SLMs near the user 
• LLMs for Sensor Programming and Code Generation
  • Develop tools that leverage LLMs to analyze sensor specifications and environmental factors, automatically generating initialization and calibration code. 
  • Develop dynamic code generation systems that adapt sensor behavior based on real-world feedback (e.g., lowering sampling rates during repetitive activities) 
  • Develop programming solutions to translate sensor data across modalities, for example, converting camera input into IMU-like data to enhance situational awareness.

Competition Rules, Details, and Suggestions

Team Size and Composition: We require teams to be composed of 2 to 5 students. The students are not required to be from the same institution and can come from different educational backgrounds (Bachelors, Masters, and PhDs). 

Judging Criteria: We will judge projects based on the below criterias:  

Innovation and Creativity: How novel the idea is, how it advances the state of the art in LLM applications for ubiquitous computing.) 

• Technical Implementation: The level of technical maturity of the demo, including the quality of integration between sensing technologies and LLMs. 

• Social Impact:  The potential positive impact of the solution on individuals and society. 

Registration Requirement: Please register for the contest and submit your idea using the form. If your team is accepted, at least one of your team members MUST pay a designated registration fee and attend the conference (or be accepted as a student volunteer, in which case they can participate for free). You will then be able to demonstrate your idea to the live audience, claim your awards, and enjoy the awesome UbiComp/ISWC conference! More details about registration requirements and financial support for student participants will be available on the main conference website soon. 

Demo Ideas: Teams will be permitted to demo only one idea; different demos of the same idea are permitted. 

Extra Equipment: Teams will be required to bring all the hardware devices needed to present the demos to the conference. No additional equipment will be provided at UbiComp. 

WiFi: WiFi is available at the conference; however, please be aware of bandwidth restrictions. Teams are welcome to use the conference WiFi as a part of their demos; however, we recommend having a Plan B, such as your own local network using routers. 

Anonymity: Submissions are not anonymous and should include your team members’ names, affiliations, and a team/project name.

Contact

For questions regarding the challenge, please reach out to the Student Challenge Chairs at sc-2025@ubicomp.org 

Student Challenge Chairs: Shantanu Pal (Deakin University, Australia), Nan Gao (Nankai University, China), Huber Flores (University of Tartu, Estonia)