Urgent.News

What's breaking now, across thousands of outlets.

AI

Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning

A long-standing goal of AI is a model that can continually learn and improve itself. On post-trained models, supervised finetuning (SFT) on new data often causes poor generalization and catastrophic forgetting. As such, the conventional wisdom is that on-policy training is a prerequisite for continual learning. In practice, however, data containing new knowledge or capabilities are often…

We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.

Read the original at arxiv.org →

More in AI

Korea's AI blind spot

As some experts have observed, technological progress has outpaced humanity’s ability to understand it and our capacity to address the problems it creates. The artificial intelligence (AI)-powered cyberattacks on Korea’s financial institutions are a vivid illustration of how ill-prepared the nation is for this new age.

More from Monday 5 October →