Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA
A JEPA-style regularizer that improves signal-to-noise ratio and preserves diversity during LLM fine-tuning.
#representation learning
Content tagged with "representation learning"
LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
A JEPA based solution for LLMs that outperforms the standard LLM training objectives and is robust to overfitting.