Reading Group & Discussion: DeepSeek-R1 and its Implications
Registration
Past Event
About Event
We'll be reading and discussing the paper: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
This landmark paper is worthy of discussion both from a geopolitical standpoint (China/US AI arms race), and from a technical perspective as they introduce a novel and highly effective method for training reasoning models.
Note:
Please review the paper before attending the reading to make the best use of the discussion.
Please RSVP by adding yourself to the Google Calendar event
We're looking forward to seeing you there!
Location