[QA] Soup to go: mitigating forgetting during continual learning with model averaging

The paper proposes Sequential Fine-tuning with Averaging (SFA) to mitigate catastrophic forgetting in continual learning, outperforming existing methods without requiring data storage or multiple parameter copies.

https://arxiv.org/abs//2501.05559

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers