Student Abstract and Poster Program

The goal of this program is to provide a forum in which students can present and discuss their work during its early stages, meet some of their peers who have related interests, and introduce themselves to more senior members of the field. The program is open to all students at the Undergraduate, Masters, and Doctoral levels.

Friday, February 28 – 11:15am – 12:30pm

The authors of some accepted abstracts will be selected to present their abstracts and their significance in a 3-minute presentation contest, to be held in a special session of the Student Abstract and Poster Program. The contest will follow the usual 3-minute thesis competition format: presentations are limited to three minutes and can be supported only by one single static slide.

All posters will be presented immediately following the SA session.

Poster Schedule

• WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
• Comparative Analysis of Demonstration Selection Algorithms for In-Context Learning in Large Language Models
• Algorithm Selection for Word-Level Hardware Model Checking
• Multimodal Commonsense Knowledge Distillation for Visual Question Answering
• Neuron Explanations for Conformal Prediction
• Beyond Virtual Points: Depth-Enhanced LiDAR-only 3D Object Detection with Semi-Supervised Learning
• Multi-Modal Hand-to-Mouth Gesture Recognition in Activity-Oriented RGB-Thermal Footage
• LLM-based Online Prediction of Time-varying Graph Signals
• Trade-Offs Between Information and Crowding in Sequential Decisions
• Understanding Unique Behavioral Patterns through Multimodal Analysis of Eye-Hand Coordination in Autistic Children
• Neuro-Guided Graph Search for Symbolic Regression
• Unraveling the Influence of Training Data and Internal Structures in Large Language Models for Enhanced Explainability
• Automating Thought of Search: A Journey Towards Soundness and Completeness
• LLM Stinger: Jailbreaking LLMs using RL fine-tuned LLMs
• Causal Explanation of Quality of Parent-Child Interactions with Multimodal Behavioral Features
• An Evaluation of Approaches to Train Embeddings for Logical Inference
• Combating Phone Scams with LLM-based Detection: Where Do We Stand?
• What Lies Beneath the Guardrails? Jailbreaking Meeting Bias Audit
• LAqua: Laplacian Pyramids for Aquatic Segmentation (Student Abstract)
• Hateful Meme Detection through Context-Sensitive Prompting and Fine-Grained Labeling
• NAAM: Node-Aware Attention Mechanism for Distilling GNNs-to-MLP (Student Abstract)

For More Information

Inquiries concerning submissions and suggestions for the student abstract and poster program may be directed to the program cochairs at aaai25sachairs@aaai.org. All other inquiries should be directed to AAAI at aaai25@aaai.org.

AAAI-25 Student Abstract and Poster Cochairs

Shirin Sohrabi (IBM Research / University of Toronto, USA)
Sarath Sreedharan (Colorado State University, USA)