Program
Program at a glance
The following is a Google Calendar for the events of the main conference. The timezone is indicated 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 at the bottom of the calendar.
Most (but not all) of the main events for the conference are held at the Leslie & Gordon Diamond Family Auditorium, Simon Frasier University.
Detailed Program
Tentative schedule, subject to changes.
Tuesday, May 26 2026
Session 2A - Efficient Deep Learning: Compression & Architecture
Room: Diamond Family Auditorium | Chair: TBA
09:30 17 EPAS: Efficient Training with Progressive Activation Sharing
09:45 25 STRESNET & STYOLO: A New Family of Compact Classification and Object Detection Models for MCUs
10:00 26 CompressNAS: A Fast and Efficient Technique for Model Compression using Decomposition
10:15 104 PICAB: A Permutation-Invariant Contextual Attention Bandit for Energy-Constrained Edge AI
11:00—11:30 • Invited talk from our Platinum sponsor, the Mental Health Commission of Canada Artificial Intelligence Guidance in Mental Health and Substance Use Health Care in Canada Katie SeguinChair: Dr. Luiza Antonie, University of Guelph
11:30—12:30 • Keynote speaker Algorithm synthesis with theoretical guarantees Kevin Leyton-Brown (University of British Columbia) Room: Diamond Family Auditorium | Chair: Dr. Sébastien Gambs, Université du Québec à Montréal
Session 2C - Graph Neural Networks
Room: Diamond Family Auditorium | Chair: TBA
14:00 73 Density-Aware Graph Generation with Learnable Edge Prediction
14:15 171 Poly-WaveGC: A Generalized Spectral Wavelet Graph Convolution Network
14:30 262 Text2Edge: Language-Aware Temporal Graph Transformer for Dynamic Link Prediction
14:45 342 Enhancing Few-shot Node Classification with High Order Graph Neural Networks
15:00 156 Attention Gated Bidirectional LSTM for Real-time Rear-end Collision Prediction in ITS
Session 2D - Computer Vision and Vision Language Models
Room: Diamond Family Auditorium | Chair: Dr. Thangarajah Akilan, Lakehead University
16:00 18 FogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather
16:15 54 QuantFormer: A Hybrid Quantum Classical Transformer for Hyperspectral Image Classification
16:30 263 Enhancing Thermal Image Object Detection using Spatial Edge-aware Attention
16:45 177 ConTrans: Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization
17:00 28 A Modular Multimodal Data Extraction Pipeline with Table Layout Correction
17:15 265 FIFA-RS: Frequency-Infused Fine-grained Alignment for Structural Anomaly Reasoning in Remote Sensing
Wednesday, May 27 2026
Session 3A - LLM Safety & Robustness
Room: Diamond Family Auditorium | Chair: Dr. Andrew R. McIntyre, Acadia University
09:00 194 Defending RAG Against Knowledge Poisoning Using Cross-Encoder Activation Signals
09:15 216 Does Context Compression Preserve Refusal Alignment?
09:30 302 Exposing LLM Safety Gaps Through Mathematical Encoding: New Attacks and Systematic Analysis
09:45 338 RAG-Safe: A Recall-First Safety Framework Comparing Open-Source and Commercial LLM Moderation Pipelines
Doctoral Dissertation Award
Room: Diamond Family Auditorium | Chair: Chair: Dr. Mark Crowley, University of Waterloo
11:00 Doctoral Dissertation Award Presentation
11:30—12:30 • Keynote speaker Language as a signal-symbol nexus for human-compatible sequential decision making Sheila McIlraith (University of Toronto) Room: Diamond Family Auditorium | Chair: Dr. Mark Crowley, University of Waterloo
Session 3C - Retrieval-Augmented Generation, Information Retrieval & Evaluation
Room: Diamond Family Auditorium | Chair: Dr. Richard Khoury, Université Laval
14:00 87 Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
14:15 97 Auditing Citation Behavior in AI-Generated Search Summaries
14:30 107 Cause-Conditioned Multi-Task Learning for Answerable Question Suggestion in MRC
14:45 210 A Meta-Analysis of Evaluation Framework Reliability and Cross-Domain Generalization
15:00 231 Citation Constraints and Reference Hallucinations in Large Language Models
15:15 211 Toward Autonomous SOC Operations: End-to-End LLM Framework for Threat Detection and Resolution
Session 3D - Natural Language Processing, Text Analytics & Data Augmentation
Room: Diamond Family Auditorium | Chair: Dr. Amine Trabelsi, Université de Sherbrooke
16:00 219 Smaller, Smarter, Greener: Reducing LLM Inference Emissions with RAG
16:15 273 NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data
16:30 281 An LLM-based Data Augmentation Method for Personas to Enhance Alcohol User Prediction
16:45 298 ToxiSight: Leveraging Moderator Expertise Through Behavioral Measurement in Gaming Toxicity Annotation
17:00 35 TASR: A Trustworthy LLM-based Framework for TCFD-Aligned Sustainability Report Analysis
17:15 288 Segmentation Expert-Mixture Regularization: An Adaptive Learning Method for Imbalanced Regression
Thursday, May 28 2026
Graduate Student Symposium (GSS) — Poster Session
Room: James Douglas Area
09:00—11:00 Please see the list of posters presented below.
Session 4A - AI for Healthcare
Room: Diamond Family Auditorium | Chair: Dr. Carson Leung, University of Manitoba
09:00 57 NLP-Assisted Case Identification and Interpretable ML for Long COVID Detection in Primary Care EMRs
09:15 134 Explainable Medical Image Segmentation via Attention-Gated Fusion of ViTs and U-Nets
09:30 163 Anatomically-conditioned Latent Diffusion Model for Few-Shot Cross-Domain 3D Glioma MRI Synthesis
09:45 261 Hardware Accelerated Privacy-Preserving Ensemble Learning for X-Ray Image Diagnostics
10:00 314 Domain-Adapted Fine-Tuning of ECG Foundation Models for Multi-Label Structural Heart Disease Screening
10:15 86 Optimizing Bayesian Neural Networks for Genomic Prediction
Session 4B - Trustworthy, Explainable & Ethical AI
Room: Diamond Family Auditorium | Chair: Leila Kosseim, Concordia University
11:00 66 An Analytical Framework for Multi-Theoretic Ethical Stress Test (MTEST) for AGI
11:15 200 Interactive Learning from Explanations with Adaptive Guidance
11:30 251 BARBiE: An Associative Rule-Based Interactive Framework for Explaining Black-Box Models
11:45 256 Vulnerability of Machine Learning Models for Gender Recognition in Virtual Reality
12:00 291 CEAR: Certified Ensemble Adversarial Robustness in DNNs
12:15 293 Are You the A-hole? A Fair, Multi-Perspective, Ethical Reasoning Framework
Graduate Student Symposium GSS — Oral Presentations
Room: Diamond Family Auditorium | Chair: Dr. Ritu Chaturvedi
14:00 Please see the list of presentations below.
Masters Dissertation Award
Room: Diamond Family Auditorium | Chair: Dr. Ritu Chaturvedi
15:00 Masters Dissertation Award Presentation
Poster Session
Room: James Douglas Area
15:30—17:30 Please see the list of short papers for poster presentation below.
Friday, May 29 2026
Session 5A - Applied AI & Optimization
Room: Diamond Family Auditorium | Chair: Dr. Paula Branco, University of Ottawa
09:00 199 Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices
09:15 72 AI-Enhanced Digital Twin System for Intelligent Battery Management
09:30 88 A Hybrid ALNS-Based Approach for the EV Routing Problem with Time Windows
09:45 233 Evaluation Protocols Under Extreme Class Imbalance: Evidence from a Newborn Screening Case Study
10:00 285 Just-in-Time Defect Prediction Using Cost-Efficient Boosting Models
10:15 69 Efficient Additive Relative Information Attention for Transformer-based Symbolic Music Composition
Session 5B - Reinforcement Learning, Agents & Recommendation Systems
Room: Diamond Family Auditorium | Chair: Dr. Luiza Antonie, University of Guelph
11:00 51 CA2: Code-Aware Agent for Automated Game Testing
11:15 117 Towards Optimizing Proximal Policy Optimization PPO through Supervised Model-Support
11:30 141 Beyond Recency Bias: Combining Sequential and Global Collaborative Signals in LLM-Based Recommendation
11:45 317 Stabilizing Black-Box Prompt Optimization with Textual Regularization and Signal Aggregation
12:00 339 AdaPrivate: Privacy-Preserving Online Learning for Recommender Systems via Contextual Bandits
Session 5C - Machine Learning Theory & Evaluation
Room: Diamond Family Auditorium | Chair: Dr. Lydia Bouzar-Benlabiod, Acadia University
14:00 68 blksprs: A Triton Library for Block-Sparse Matrix Operations
14:15 140 Back to the Future: Revival of Evidence Theory and Modal Logic for Robust and Interpretable AI
14:30 153 Expanding AI Literacy: How Emotional Intelligence Supports Productive Uncertainty
14:45 24 Lightweight Neuro-Symbolic Anomaly Detection of Traffic
Session 5D - Temporal Modelling, Time-Series & Forecasting
Room: Diamond Family Auditorium | Chair: Dr. Yves Lucet, University of British Columbia
16:00 143 ADAPTive Input Training for Many-to-One Pre-Training on Time-Series Classification
16:15 167 Physics-Guided Diffusion Models for Production Forecasting with Limited Well Data
16:30 269 Directional Stock Prediction with Temporal Sentiment
16:45 343 Reinforcement Learning-Based Wind Farm Layout Optimization Using Neural Surrogate Models
Full Papers for Oral Presentation
Please see the above schedule.
Short Papers for Poster Presentation
Thursday, 28 May, 15:30-17:30 | Room: James Douglas Area
6 Visualizing the Elimination of Arbitrary Variables in Bayesian Networks as Compound Bayesian Networks
11 Struct-SQL: Distilling Structured Reasoning for Small Text-to-SQL Models
44 Query Refinement in Dense Retrieval Using LLM-Driven Relevance Feedback
58 Real-Time Jailbreak Detection via Safety-Weighted Semantic Entropy Probes
61 Waste-Container Lifting Using Residual Reinforcement Learning On Large-Scale Crane with Underactuated Tools
65 When Do LLMs Listen? Confidence-Guided Knowledge Acceptance in LLMs
75 LLM-Enhanced Hypergraph Learning for Review-Based Cross-Domain Recommendation
79 Reducing Representation Bias through Fairness-Driven Sampling in Contrastive Learning
81 GitHub's Copilot Code Review: Can AI Spot Security Flaws Before You Commit?
85 Optimizing RAG for Academic Advising: A Hybrid Routing and Metadata Filtering Approach for Enhanced Accuracy and Efficiency
108 Multi-Objective Reference-based Machine Unlearning
123 An Empirical Study of Attention-Based Cross-Modal Retrieval for Movies
133 Diffusion-based Long and Short Term Interest Sequence Recommendation
145 A Flexible Fair Learning Framework via Group-Aware Surrogate Loss Reweighting
147 VOLTS: Validated Output through Logit Tree Search for Reliable PDDL Planning with Small Language Models
150 From Tweets to Model-Based Causal Spans: Noise-Robust Transformers for Social Media Sentiment Analysis in the Age of LLMs
154 Probabilistic TopK Sparse Autoencoder for Interpreting the Activations of Large Language Models
158 Neuro-Symbolic Adaptive Collaboration of Arena-Based Argumentative LLMs for Contestable Legal Reasoning
159 Learning Adaptive Wiener Processes for Stochastic Financial Datasets with Physics-Informed Kolmogorov-Arnold Encoder-Decoder Networks
188 Towards Custom AI Benchmarking for the Government of Canada
192 Lexicon-Guided Morphological Tag Injection for Low-Resource Filipino-Cebuano Neural Machine Translation
195 Diagnosing and Repairing Factual Errors in RAG under Budget Constraints
197 Sequence-Based Evolutionary and Neural Strategies for Reducing Zone Crossings in Toolpaths
212 Enhancing Stability in Rule-Based Post-Hoc Explanations
221 Disentangling dataset size from synthetic diversity in tuberculosis chest X-ray classification
230 The Reliability Gap: A Multi-Dimensional Technical Audit of Memory Safety and Logical Integrity in LLM-Generated C Code
255 CERA: Context-Engineered Reviews Architecture for Synthetic Dataset Generation
257 A Quantitative Evaluation Protocol for Assessing the Clinical Usefulness of 3D Saliency Explanations for MRI-based Alzheimer’s Classification
264 Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning
277 Contextual Stance-Aware Semantic Graph Learning for Fake News Detection
278 To correct or not to correct?: Assessing the multiple comparisons problem for association rule mining of environmental DNA (eDNA) detection survey datasets
279 Evaluating Role-Based Prompt Architectures in In-Context Learning
280 Representation Effects in Child and Youth Mental Health Emergency Readmission Predictions
282 LLM Sycophancy: How Users Flag and Respond
303 Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection
305 GlossAdapter: Enhancing word sense disambiguation via LoRA adapters
307 Beyond Information Sufficiency: Observation-Action Space Alignment in Robotic Reinforcement Learning
310 From Hints to Answers: Uncertainty-Aware LLM-Guided Retrieval for Multi-Hop Question Answering
152 Output-Distribution Divergence as a Pre-Interpretation Gate for Mental Health AI
183 SAMURAI: A Two-Stage Foundation Model Pipeline for Robust Optic Nerve Head Segmentation in Fundus Images
207 Personalized Stability Triggers: A Model-Agnostic Framework for Adaptive Early Prediction of At-Risk Students in Education
227 Scaling Limits of Deep Reinforcement Learning: A Stability Analysis with Maximal Update Parametrization
241 Toward Believable Health & Wellness Conversational Agents: A Post-LLM Turing-like Evaluation Framework (Position Paper)
260 Calame: An Open Source Transcription Software
340 Interpretable Dynamic Rule Attention for Medical Coding
341 Uncovering Latent Subgroups: Spectral Clustering for Fairness Analysis in Contrastive Embeddings
205 Measuring the LEAK: A Fine-Grained Metric for Partial Information Leakage in Jailbreaking of LLMs, Dakota Staples (UNB)*
Graduate Student Symposium
Thursday, 28 May 2026, 9:00-11:00 | Room: James Douglas Area
306 Execution Aware A* for Cross Exchange Stablecoin Arbitrage
331 On Efficient Computational Methods for Transformer-Based Symbolic Music Generation
332 A Generalizable AI-Driven Decision Support System for Infectious Disease Modeling
336 Fed-Universe: A Semantic-Geometric-Topological-Human (S-G-T-H) Stack for Negotiated Alignment in Federated Systems
344 Clinical Trial Recommendation with LLM-Based Query Generation and Graph-Based Pairwise Re-ranking
323 Bridging the Multilingual Emotion Gap: Unified Modeling and Evaluation of Transformers, Hybrid Architectures, and Large Language Models for Low-Resource African Languages
328 Pure Leveled CKKS for CNN Inference: The Finite Limb Depth Bound and ResNet-20 Stress-Test
335 Reclaiming the Loop: From the Consensus Trap to Pluralistic Data Annotation
175 Measuring and Closing the Retrieval Gap in Financial Question Answering
191 ASHC: Quantum-Inspired Hierarchical Clustering for Priority-Aware Coverage Path Planning
246 Multi-Dimensional Model Integrity and Responsibility Assessment Index and Scoring Framework
271 RotIE: Rotary Informational Embeddings for Symbolic Music Generation
308 Next-Generation AI Vegetation Analytics: Low-Cost PSRI Translation from RGB and NDVI for Precision Crop Monitoring
130 STRIDE Moves Market Sentiment
185 Cluster-Aware Retrieval-Augmented Generation with Hybrid Retrieval for Faithful Medical Report Summarization
74 Fairness Audits of Institutional Risk Models in Deployed ML Pipelines
14:00 - 15:00 Oral presentation
Room: Diamond Family Auditorium
In addition to oral presentation, authors of the following five GSS papers also present their posters in the GSS poster session.
306 Execution Aware A* for Cross Exchange Stablecoin Arbitrage
331 On Efficient Computational Methods for Transformer-Based Symbolic Music Generation
332 A Generalizable AI-Driven Decision Support System for Infectious Disease Modeling
336 Fed-Universe: A Semantic-Geometric-Topological-Human (S-G-T-H) Stack for Negotiated Alignment in Federated Systems
344 Clinical Trial Recommendation with LLM-Based Query Generation and Graph-Based Pairwise Re-ranking
Industry/Government Track (Wednesday, May 27th)
14:00 - 17:30 : Industry track
Session Chair: Annie Ying, GitLab
Industry/Government Track Speakers
14:00-15:00 Panel 1: Open Model and Open Access in AI
Moderator: Newvick Lee (GitLab)
Panelists: Kris Krug (BC + AI Ecosystem), Dr. Jekaterina Novikova (Vanguard), Dr. Annie Ying (GitLab)
15:00-15:30 Invited Talk: Research from pixels to proteins: scaling generative AI for scientific discovery, by Dr. Karsten Kreis (NVIDIA)
16:00-17:00 Panel 2: Navigating AI Safety Challenges
Moderator: Alka Tandan (Reframe & Refine)
Panelists: Panelists: Robert Barton (Cisco Systems), Dr. Eric Brochu (Microsoft), Dr. Eric Oosenbrug (BC Public Service), Dr. Annika Rosanowski (Mitacs)
