Presented by
Osmosis Event Calendar
Osmosis helps companies fine-tune open-source models with reinforcement learning that outperform leading models on agentic tasks.
Hosted By
About Event
RL IRL is a one-day forum for researchers & engineers to learn more about the future of reinforcement learning, and how reinforcement learning is applied in production today.
Co-hosted by Osmosis, Reducto, Greptile, Encord, HUD, and ZeroEntropy.
Breakout Sessions:
- Andy and Abhinav (Osmosis + Greptile): Designing Your Product for RL
- Jay and Lorenss (HUD + TLDC): Building & Scaling RL Environments
- Evan (Reducto): RL for Ill-Defined Objectives
- Nicholas (ZeroEntropy): Scaling Reranker Models with RLAIF
- Frederik (Encord): Data Scaffolding for Multimodal RL
- Anshul (Turing): RL Environments for Enterprise
Presented by
Osmosis Event Calendar
Osmosis helps companies fine-tune open-source models with reinforcement learning that outperform leading models on agentic tasks.
Hosted By