Demonstration Program

The AAAI-25 Demonstrations Program is intended to foster discussion and exchange of ideas among researchers and practitioners from academia and industry by presenting software and hardware systems and research prototypes of such systems, including their capabilities and workings. All accepted demos will be allocated time for live demonstrations. Accepted demonstrations will also have a short paper included in the proceedings.

Note that AAAI-25 is planned to be an in-person conference, thus at least one author of every accepted demo will be expected to present the work in person.

Demonstrations will be held during the poster sessions. The list of demos scheduled on each day is available below.

Demo presenters: each demo will be provided with the following resources:

• (1) 6’ x 30”H draped table
• (2) side chairs
• (1) monitor on stand
• (1) 4’ x 8’ poster board 
• (1) 5 amp outlet

Program Overview

A Multi-Style Chinese Characters Writing Intelligent Tool Based on Small-scale Training Data

Accessible Hardware Implementation for Multi-Agent Collective Construction

Agent Trajectory Explorer: Visualizing and providing feedback on agent trajectories

Agentic AI for Digital Twin

An Automated Explainable Educational Assessment System Built on LLMs

An LLM-Guided Tutoring System for Social Skills Training

AutoMV: an Autonomous Agent Framework for Real Estate Marketing Video Generation

Bidirectional Human-AI Learning in Real-Time Disoriented Balancing

ClinicalRAG: Automating Pharmaceutical Label Quality Control with Hierarchical RAG and Large Language Models

Data Wrangling task automation using Code-Generating Language Models

ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant

EvalAssist: LLM-as-a-judge simplified

Falcon Medical Visual Question Answering

GODDS: The Global Online Deepfake Detection System

Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters

Human-AI Interaction using Linguistic Reasoning and Computational Chemistry for Trustworthy Materials Discovery

Incident Diagnosing and Reporting System based on Retrieval Augmented Large Language Model

InstantPainting: Expanding GANs for Efficient Text-Conditioned Image Generation Platform

LLM Attributor: Interactive Visual Attribution for LLM Generation

MAFT: Multimodal Automated Fact-Checking via Textualization

MathMistake Checker: A Comprehensive Demonstration for Step-by-Step Math Problem Mistake Finding by Prompt-Guided LLMs

MATWA: A Web Toolkit for Matching under Preferences

MerryQuery: A Trustworthy LLM-Powered Tool Providing Personalized Support for Educators and Students

MicroFiberDetect: An Application for the Detection of Microfibres in Wastewater Sludge based on CNNs

Neurosymbolic Reinforcement Learning: Playing MiniHack With Probabilistic Logic Shields

Pic2Prep: A multimodal conversational agent for cooking assistance

PRIORITY2REWARD: Incorporating Healthworker Preferences for Resource Allocation Planning

QGen Studio: An Adaptive Question-Answer Generation, Training and Evaluation Platform

Question-guided Insights Generation for Automated Exploratory Data Analysis

Real-Time Object Detection and Skeletonization for Motion Prediction in Video Streaming

Rewind and Render: Towards Factually Accurate Text-to-Video Generation with Distilled Knowledge Retrieval

RLLTE: Long-Term Evolution Project of Reinforcement Learning

SDAS: Semantic Data Acquisition System for Minimizing Redundancy and Maximizing Diversity

SPASCA: Social Presence and Support with Conversational Agent for Persons Living with Dementia

Speech is not enough: Interpreting nonverbal indicators of common knowledge and engagement

StarVector: Generating Scalable Vector Graphics Code from Images and Text

SuBiTO: Synopsis-based Training Optimization for Continuous Real-Time Neural Learning over Big Streaming Data

SummPilot: Bridging Efficiency and Customization for Interactive Summarization System

SWIFT: A Scalable lightWeight Infrastructure for Fine-Tuning

TRACE-CS: A Synergistic Approach to Explainable Course Scheduling Using LLMs and Logic

TRANSFORMER EXPLAINER: Interactive Learning of Text-Generative Models

Usage Governance Advisor: from Intent to AI Governance

For More Information

Inquiries concerning demonstration submissions and suggestions may be directed to the demonstration program cochairs at aaai25dpchairs@aaai.org. All other inquiries should be directed to AAAI at aaai25@aaai.org.

Demonstration Program Cochairs

Noa Agmon (Bar-Ilan University, Israel)
Fei Fang (Carnegie Mellon University)
Felipe Meneguzzi (University of Aberdeen)