Ernest Ryu
@ErnestRyu
Professor of Applied Mathematics at UCLA. Interested in deep learning and optimization.
New lecture recordings on RL+LLM! 📺 This spring, I gave a lecture series titled **Reinforcement Learning of Large Language Models**. I have decided to re-record these lectures and share them on YouTube. (1/7)
A thoughtful analysis by @ErnestRyu but it is missing one key insight. To bring the AI model even to IMO gold level, one has to train it to generate new questions and then solve them. (There aren't enough human-generated questions for training.) This is a key idea in Deepmind's…
Two cents on AI getting International Math Olympiad (IMO) Gold, from a mathematician. Background: Last year, Google DeepMind (GDM) got Silver in IMO 2024. This year, OpenAI solved problems P1-P5 for IMO 2025 (but not P6), and this performance corresponds to Gold. (1/10)
Thank you Ernest for your insights! Now Gemini’s IMO 2025 🏅is officially announced in our side. Excited to see how deep LLM can reason in natural language space! Will see how this will impact math education and research 😊 deepmind.google/discover/blog/…
Two cents on AI getting International Math Olympiad (IMO) Gold, from a mathematician. Background: Last year, Google DeepMind (GDM) got Silver in IMO 2024. This year, OpenAI solved problems P1-P5 for IMO 2025 (but not P6), and this performance corresponds to Gold. (1/10)