JOLT launches
The story so far
NVIDIA and researchers from Perplexity have launched JOLT, a post-training method for language models. It uses joint online learning and teaching, where a single model plays the roles of both teacher and student. The teacher model receives privileged information and accepts KL punishment to approach the student model, while the student model learns through token-level distillation signals from the teacher model.
AI-written from the reports · Updated 27 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- MarkTechPostPerplexity and NVIDIA Researchers Introduce JOLT: a Joint Teacher-Student Reinforcement Learning Method
Perplexity and NVIDIA have jointly launched JOLT, a post-training method for language models that uses joint online learning and teaching, where a single model plays both teacher and student roles. The teacher model receives privileged information and accepts KL punishment to approach the student model, while the student model learns through token-level distillation signals from the teacher model.