Toronto ML/Systems Reading Group
Meetup to discuss topics on machine learning and systems, similar to the McGill ML Reading Group - list of topics & articles below - all are welcome! 🎉
Schedule & Reading List
6:00 PM - welcome and intros
6:20 PM - topic 1: how can we make LLM evals relevant?
"Do Large Language Model Benchmarks Test Reliability" by Joshua Vendrow et al.
6:35 PM - topic 2: when is a system 100% safe?
"Jailbroken: How Does LLM Safety Training Fail?" by Alexander Wei et al.
6:50 PM - topic 3: how can we make ML models accessible for everyone?
7:05 PM - open floor discussion - bring your favourite topics!
7:15 PM - wrap up & social
Additional Resources On Topics 1-3
(1. evals) "Successful language model evals" by Jason Wei
(2. model safety) "Leveraging Mechanistic Interpretability for Red-Teaming: Haize Labs x Goodfire" by Haize Labs
(3. smaller models) "s1: Simple test-time scaling" by Niklas Muennighoff et al.
Other Reads!
(robots) "π0: Our First Generalist Policy" by Physical Intelligence
This meetup is sponsored by Rootly (YC S21)!
Rootly (YC S21) is a fast-growing Canadian startup trusted by industry leaders like NVIDIA, LinkedIn, and Wealthsimple to supercharge their on-call and incident response. Our platform seamlessly integrates with your entire tech stack and leverages AI to help SREs and DevOps teams resolve issues faster, reduce downtime, and prevent repeat incidents.