MIT's MeMo lets teams swap in a better LLM without retraining (opens in new tab)
Enabling LLMs to acquire new knowledge after training remains a major hurdle for enterprise AI — current solutions are either too expensive, too slow, or constrained by context window limits.The modular architecture works with both open- and closed-source models and sidesteps the complexity of RAG pipelines and full model retraining.Experiments show that MeMo handles complex queries reliably even when retrieval pipelines are noisy. It avoids the catastrophic forgetting associated with direct ...
Read the original article