Program
Program at a Glance
The following is a Google Calendar for the events of the main conference. You can consult the proceedings of the conference on the open access platform PubPub
. The program schedule for Responsible AI is here.
The timezone is indicated by Google in the lower left corner of the calendar.
Click on individual events for more details. You can add the whole calendar to your agenda by using the link in the lower left corner.
Most events take place at the Taylor Institute for Teaching and Learning (Google Maps), in Room 160 (ground floor plan).
The banquet on Wednesday will be held in Hall AB - MacEwan Student Centre, 402 Collegiate Blvd NW, Calgary.
Detailed Program
Most events take place at the Taylor Institute for Teaching and Learning (Google Maps), in Room 160.
The banquet on Wednesday will be held in Hall AB - MacEwan Student Centre, 402 Collegiate Blvd NW, Calgary.
Monday, 26 May 2025
9:00 — 9:30 Welcome and Opening Remarks
9:30 — 10:30 Session 1 - Knowledge Representation
Room 160
Chair: Yifeng Li
9:30 67 On the Semantics of Actual Causality in Situation Calculus Concurrent Game Structures
9:50 185 Dynamic Causal Attention with Sparse Temporal Networks for Interpretable Causal Discovery in Multivariate Time Series
10:10 198 SAT for Upward Book Embedding: An Empirical Study
11:00 — 12:30 Session 2 - Reinforcement Learning and Optimization
Room 160
Chair: Yash Vardhan Pant
11:00 2 SPADE: Solving the Multi-Depot Vehicle Routing Problem with Inter-Depot Routes Using Multi-Agent Deep Reinforcement Learning
11:18 28 The QBF Cover encoding for Harary Tic-Tac-Toe’s
11:36 34 Towards Inference in Arithmetic Circuits by Exploiting Barren Variables
11:54 113 Balanced-Boundary IoU: A Holistic Algorithm Towards Improving Segmentation Evaluation Metric
12:12 150 Agile Reinforcement Learning for Real-Time Task Scheduling in Edge Computing
14:00 — 15:00 Session 3 - Speech and Language
Room 160
Chair: Vasile Rus
14:00 73 Neural Wavelet Packet-Based Bidirectional Autoencoder for Multi-Resolution Speech Enhancement
14:20 166 The Power of Adaptation: Boosting In-Context Learning through Adaptive Prompting
14:40 170 Attenuating Catastrophic Forgetting of Token-Level Knowledge in Contrastive Sentence Embeddings with Attentive Pooling
15:30 — 17:00 Session 4 - AI Applications I - Medical and Biological Applications
Room 160
Chair: Sirisha Rambhatla
15:00 23 Improving Patient-Clinical Trial Matching Using Convolution Neural Networks
15:18 50 InceptoFormer: A Multi-Signal Neural Framework for Parkinson’s Disease Severity Evaluation from Gait
15:36 59 Transfer Learning for Multi-Lead ECG Analysis in Cardiac Arrest Risk Classification
15:54 155 Real-Time Plant Disease Detection Using YOLOv8 on a Low Resources Device
16:12 200 A Comparison of Autoencoders and Variational Autoencoders for Anomaly Detection in Dermoscopic Skin Lesion Imagery
Tuesday, 27 May 2025
11:00 — 12:30 Session 5 - Large Language Models (LLMs) and Natural Language Processing (NLP)
Room 160
Chair: Richard Khoury
11:00 162 On the Influence of Discourse Relations in Persuasive Texts
11:18 103 Enhancing Memory Recall in LLMs with Gauss-Tin: A Hybrid Instructional and Gaussian Replay Approach
11:36 106 Let’s CONFER: A Dataset for Evaluating Natural Language Inference Models on CONditional InFERence and Presupposition
11:54 158 On Pre-training and Self-training
12:12 81 Aligning Language Models Using Multi-Objective Deep Reinforcement Learning
14:00 — 15:00 Session 6 - Machine Learning – Classification
Room 160
Chair: Yan Yan
14:00 24 Fast Graph Neural Network for Image Classification
14:20 128 Enhancing Predictive Coding Networks for Multi-Modal Generation and Classification
14:40 145 Reliability-Driven LiDAR-Camera Fusion for Robust 3D Object Detection best paper award
15:30 — 17:00 Session 7 - Applications II - Security, Adversarial ML, and Anomaly Detection
Room 160
Chair: Sébastien Gambs
15:30 94 On the Impact of Imbalance Handling Techniques in Deep Learning Models for Malware Detection
15:48 164 Generating Malicious Demonstration Policies to Exploit Vulnerabilities in Inverse Reinforcement Learning
16:06 177 Detecting Aimbot Usage in Minecraft Using a Long Short-Term Memory Model
16:24 188 SAGNN+CS: A Resilient Graph Neural Network Framework Against Backdoor Threats
16:42 203 Handling Concept Drift in Fraud Detection: A Replication Study
Wednesday, 28 May 2025
11:00 — 12:30 Session 8 - Vision and Multimodal Systems
Room 160
Chair: Rachid Hedjam
11:00 95 Multimodal Emotion Recognition with Cross-Attentive Learning and Feature Fusion
11:18 98 MAC: Multimodal Attentive Contrastive Learning Framework
11:36 65 Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models
11:54 127 Taxonomic Reasoning for Rare Arthropods: Combining Dense Image Captioning and RAG for Interpretable Classification
12:12 184 Contextual Attention-Based Multimodal Fusion of LLM and CNN for Sentiment Analysis
14:00 — 15:00 Graduate Students Symposium
Room 160
Chairs: Kristina Kupferschmidt and Ulrich Aïvodji
Oral presentations
14:00 Welcome & Introduction
14:04 From Data Annotation to AI Prediction: Streamlining Histopathology Analysis in Acute Respiratory Distress Syndrome
14:20 C++ Source Code Verification Pipeline
14:40 Towards Backstepping Control of a Quadrotor Uncrewed Aerial Vehicle on SE(3)
Poster presentations
Toward a Deep Reinforcement Learning Framework for Efficient Uncrewed Aerial Vehicle Control System in Dynamic Environments
Advancements in Large Language Models Through Employment of Retrieval Augmented Generation and its Enhancements for Assistance in Academia
C++ Source Code Verification Pipeline
Deep Learning Approaches for Soil Moisture Prediction
Deep learning prediction of bacterial genetic engineering using a hybrid CNN-transformer approach
Enhancing Quadrotor Flight Accuracy: Extended and Unscented Kalman Filter Estimation in SE(3)
Frame Problem and Obligation-Producing Actions
From Data Annotation to AI Prediction: Streamlining Histopathology Analysis in Acute Respiratory Distress Syndrome
Mixture-of-Experts for Time Series Imputation
Position and Attitude Trajectory Tracking Control for Advanced Aerial Manipulators Manipulating a Priori Unknown Objects
Towards Backstepping Control of a Quadrotor Uncrewed Aerial Vehicle on SE(3)
15:30 — 17:00 Session 9 - Short Papers POSTERS
Room TI Gallery
53 Continual Prediction Learning Techniques to Support Users' Grasp Selection on a Multi-Articulating Prosthetic Hand
56 3D Gaussian Splatting and Camera Poses Joint Optimization for Motion Blur Images via Low-pass Filter
68 How Robust Are Higher-Order Graph Neural Networks to Backdoor Attacks?
79 Analysis of Canadian Wildfire Tweets Over Seven Years
121 Evaluating the Effectiveness of Cost-Efficient Large Language Models in Benchmark Biomedical Tasks
123 A Context-Aware LLM-Based Action Safety Evaluator for Automation Agents
131 Vectorized Context-Aware Embeddings for GAT-Based Collaborative Filtering
146 SF2D: Semi-supervised Federated Learning for Fall Detection using (Un)labelled Data in Edge-Cloud
153 Discovering and Evaluating Politeness Editing Strategies
189 Comparing Traditional and Deep Learning Approaches for Product Matching: Performance on Unseen Entities
191 A Minimalist Swarm Robotic Controller for Foraging
195 Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNet
197 From Control to Flourishing: Responsible Generative AI and the Limits of Meaningful Human Control
202 Intra-Layer Recurrence in Transformers for Language Modeling
Thursday, 29 May 2025
11:00 — 12:30 Session 10 - Explainability, Interpretability, Ethics and Safe AI
Room 160
Chair: Osmar Zaiane
11:00 4 Topology-Driven Solver Selection for Stochastic Shortest Path MDPs via Explainable Machine Learning
11:18 42 Enhancing Legal Text Entailment: Evaluating Model Architectures, Training Approaches, and Interpretability
11:36 48 XGD: Explainable AI-Guided Knowledge Distillation with Feature Refinement for Semantic Segmentation
11:54 108 Faithful Perturbations and Evaluations for Post-Hoc Local Explanation Methods
12:12 130 Ethical Risk Assessment of the Data Harnessing Process of LLM supported on Consensus of Well-known Multi-Ethical Frameworks
14:00 — 15:00 Session 11 - Machine Learning and Interpretability
Room 160
Chair: Diana Inkpen
14:00 32 Meta-Unsupervised Representation Learning: A New Approach to Factorization and Interpretability best student paper award
14:20 41 Unsupervised Feature Selection Using Orthogonally Constrained Matrix Factorization with Hessian Regularization and Non-Convex Sparsity
14:40 196 Discrete-Survival Compatibility Score for Donor-Recipient Matching in Liver Transplantation
15:30 — 16:24 Session 12 - Applications III - Financial and Cryptocurrency Market Applications
Room 160
Chair: Bijan Raahemi
15:30 18 A Domain-Specific Transformer Approach for Financial Statement Fraud Detection
15:48 119 Financial Market Prediction using Contrastive Learning-based News Representation and Multi-Resolution Market Data
16:06 125 Enhancing Cryptocurrency Price Prediction by Applying Temporal Fusion Transformers on Subseries
