​Frontier AI Safety & Efficient RAG

​This event looks at two active areas of AI: how the frontier AI safety ecosystem is developing, and recent approaches for making retrieval-augmented generation more efficient.

​The talks will explore two perspectives:

• ​🛡️ Frontier AI Safety Ecosystems: How the ecosystem connecting people, institutions, resources, and ideas is developing, where coordination and capacity might be strengthened, and what recent efforts suggest about responding to risks from AI sysgems.

• ​🧠 Efficient Retrieval-Augmented Generation: Recent research on RAG, with a focus on methods for making retrieval more efficient and improving how language models find and use external information.

​This session is for AI engineers, researchers, founders, product builders, data scientists, students, and anyone interested in current developments in AI.

​🗓️ Program

​5:30 PM – 5:50 PM 👋 Arrival & networking

​Doors Close at 5:45 PM

​5:50 PM – 6:05 PM 🎙️ Issam Laradji | Biases in LLM-as-a-Judge for Evaluating AI Agents

​6:10 PM – 6:50 PM 🛡️ Krystal Pan | Field Notes on the Frontier AI Safety Ecosystem

​6:50 PM – 7:00 PM ☕ Break

​7:00 PM – 7:40 PM 🧠 Amirhossein Abaskohi | Latest Developments in Efficient Retrieval-Augmented Generation

​7:40 PM – 8:00 PM 🤝 Closing & networking

​Timing is approximate and may shift slightly based on audience questions and discussion.

​ℹ️ Disclaimers

​🫧 Feel free to bring your own food and water bottle.

​💧 There is a water fountain at the venue.

​🚗 Paid parking is available nearby, including EasyPark.

​🐾 The venue is not pet-friendly (service animals welcome).

​🚲 Bicycles are not permitted inside the building.

​⏰ Doors close at 5:45 PM, so please arrive before then.

​🏢 Before 5:45 PM, someone in the lobby can guide you to the event space on the 14th floor.

​🎤 Speaker 1: Krystal Pan

​Co-Founder, Vancouver AI Safety Hub | Founder, Increment AI Lab

​Krystal Pan is a co-founder of the Vancouver AI Safety Hub and founder of Increment AI Lab. Her work focuses on frontier AI safety ecosystem-building and building technical common ground across governance and adjacent fields. She holds an MSc in Computer Science from McGill University and Mila and was a Google DeepMind Scholar.

​Talk: Field Notes on the Frontier AI Safety Ecosystem

​Frontier AI safety is shaped not only by technical research and policy, but by the wider ecosystem connecting people, institutions, resources, and ideas.

​Krystal will share evolving observations on how that ecosystem is developing, where coordination and capacity might be strengthened, and what recent efforts suggest about building an ecosystem better able to respond to risks from transformative AI. She will also discuss some of the gaps she has encountered and the experiments she is building in response through the Vancouver AI Safety Hub (VASH) and Increment AI Lab.

​🎤 Speaker 2: Amirhossein Abaskohi

​PhD Student, Computer Science, UBC | UBC NLP Group

​Amirhossein Abaskohi is a PhD student at the University of British Columbia, supervised by Prof. Giuseppe Carenini and Prof. Peter West. He previously earned his MSc in Computer Science from UBC with distinction, supervised by Prof. Giuseppe Carenini and Prof. Issam Laradji. His research focuses on natural language processing, with recent work exploring retrieval-augmented generation and how retrieval can be made more efficient.

​Talk: Latest Developments in Efficient Retrieval-Augmented Generation

​Drawing from his recent PhD research papers, Amir will present recent developments in retrieval-augmented generation, with a focus on methods for making retrieval more efficient. He will discuss new approaches, findings, and open questions from this work and what they suggest for building more efficient RAG systems.

​🎙️ Opening: Issam Laradji

​Adjunct Professor, UBC

​Opening: Biases in LLM-as-a-Judge for Evaluating AI Agents

​LLMs are increasingly used as judges to evaluate AI systems and agents. However, these evaluations can be affected by systematic biases.

​Issam will introduce several known biases in LLM-as-a-Judge evaluation, how they can influence evaluation results, and what they mean when using LLMs to evaluate AI agents.

​🌲 About

​Vancouver AI Meetup (VAM!) is a community of researchers, engineers, founders, students, and AI practitioners who come together to learn, share ideas, and discuss the latest developments in artificial intelligence.

​Northeastern University was founded in 1898 and is a global research university and leader in experiential lifelong learning. With campuses across the U.S., U.K., and Canada, over 320,000 alumni, and more than 3,800 partners worldwide, Northeastern's global university network serves as a platform for scaling ideas, talent, and solutions.

​Located in the heart of downtown Vancouver, the Vancouver campus offers a wide range of master's-level technology programs, including pathway programs that allow students with non-STEM backgrounds to pursue graduate studies in technology.