LLM & Applications | Canadian AI Conferen

LLM & Applications Workshop at the Canadian AI Conference

Large Language Models (LLMs) are transforming AI with their powerful natural language processing capabilities. This workshop provides a platform to explore the latest advancements, applications, and challenges in LLMs while fostering collaboration between researchers, practitioners, and students.

Key objectives include:

Showcasing novel applications in healthcare, personal assistants, information extraction, among others.
Addressing challenges in fine-tuning, alignment, scalability, and efficient inference.
Providing hands-on tutorials for students and newcomers.

Topics of Interest

LLMs, Prompt Engineering, Fine-Tuning
Efficient Architectures, LLM-based Agents, Multi-Modal Models
Real-Time Inference, AI Safety, Evaluation Techniques

Keynote Speakers

Hamidreza Eslami, Director, Fraser Health Authority
Xiaoxiao Li, CIFAR AI Chair, University of British Columbia

Organizers

Najeeb Khan, Ph.D. – Applied Scientist, Amazon
Farhad Maleki, Ph.D. – Assistant Professor, University of Calgary
Alireza Morsali, Ph.D. – Senior Data Scientist, Global Relay

Call for Participation

We invite researchers, practitioners, and students to submit papers (up to 6 pages) on topics such as:

Novel LLM Applications (personal assistants, healthcare, etc.)
Prompt Engineering Techniques
Fine-Tuning & Alignment Strategies
Efficient Architectures & Optimization
Evaluation Methods for Practical Use Cases

🔗 Paper Submission Form

Workshop Highlights

Keynote Talks – Presentations by leading experts in LLM research.
Paper Presentations – Showcase of innovative research & applications.
Hands-on Tutorials – Practical sessions covering:

Advanced Prompting Techniques & RAG
Alignment & Fine-Tuning Strategies
LLM Evaluation Methods
Efficient Inference Techniques

Important Dates

Paper Submission Deadline: May 1, 2025 AoE
Notification of Acceptance: May 15, 2025
Workshop Date: May 26, 2025

Workshop Location

Taylor Institute, Room 148

Workshop Schedule

09:30-10:00 | Keynote: Responsible Innovation: Revolutionizing Healthcare with Generative AI
10:00-10:30 | Keynote: Foundation Models in Healthcare: Advances, Pitfalls, and Path Forward
10:30-11:00 | Coffee Break
11:00-12:00 | Session 1 - Intro to LLM
12:00-12:10 | Presentation: Automatic Extraction of Performance Metrics from the Scientific Literature
12:15-12:25 | Presentation: Using Negative Nudging to Measure LLM Hallucinations
12:30-02:00 | Lunch
02:00-03:00 | Session 2 - Finetuning
03:00-03:30 | Coffee Break
03:30-04:00 | Building AI systems with Databricks
04:00-05:30 | Session 3 - Agentic AI

Workshop Starter Repo

Github link