Join us to learn how to:

• Explain the full LLM training stack and where RL fits
• Choose between PPO/DPO/GRPO/GSPO for real use cases
• Design reward signals (including verifiable rewards)
• Debug RL fine-tuning with practical diagnostics

ENROLLMENT RATES: 

• Early bird rate: $1,500 USD (until July 28, 2026)
• General admission rate: $2,000 USD (starting on July 29)
• Student rate: $350 USD. You must use your university or educational institution email account when registering and use the discount code "LOVETOLEARN2026". You will receive a confirmation email if you're approved. 

Go back to main page