Columbia forum on OC-GRPO: RL post-training for teaching LLMs new skills
ceciletamura · x · 2026-11-05
A research forum announcement: AgPriyank of Columbia will discuss OC-GRPO work with ceciletamura of ploutosai, on how RL can help LLMs learn to solve problems they currently can't.
Topics include learning from guided rollouts, challenges of RL post-training, and future directions. Scheduled Nov 5, 4 PM Pacific, with a livestream link.
More from Companies & People
- Intuit CEO Sasan Goodarzi on Stratechery: turning accountants from channel into customers with AI — Stratechery · 2026-11-05
- Robotics Startup Mundane Hiring Mechanical Engineers at $175K-$260K for Teleoperated Robots — chris_j_paxton · 2026-11-05
- Hugging Face crew runs grand hackathon in Doha with QAI through Dec 7 — RisingSayak · 2026-11-05
- Shenzhen GEO Conference lineup revealed: WaytoAGI founder AJ to speak on overseas growth — vista8 · 2026-11-05
- Blackstone and Norm AI CTOs: agent capability made our workflow code obsolete — AI Engineer · 2026-11-05
- Practical AI podcast: how organizations set AI boundaries and deploy agents — Practical AI · 2026-11-05