Perplexity and NVIDIA Researchers Introduce JOLT: a Joint Teacher-Student Reinforcement Learning Method
Perplexity’s JOLT trains one model as teacher and student, matching GRPO’s MATH accuracy with 6.5x fewer training tokens.
MarkTechPost · Asif Razzaq · https://www.facebook.com/MarkTechPost/
Entities: NVIDIAPerplexity