**********
Paper #20: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
When: 1:30PM, 6/Feb/2025
Where: C6.3.26
**********

Don’t forget to read the paper beforehand and come prepared with a contribution!

**********
How the reading club works:
– Happens every 2 weeks;
– Presenter chooses a paper and summarises it in no more than 10 minutes (slides optional);
– The goal of the club is to promote the exchange of ideas, so read the paper beforehand and come prepared with comments or questions.