Overcoming the Stability Gap in Continual Learning · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2306.01904/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTOvercoming the Stability Gap in Continual Learning — mentioned by chriskananhttps://news.ycombinator.com/item?id=40392509urn:hackerpapers:mention:2306.01904:40392509Fri, 17 May 2024 17:54:38 GMT<p>This study is great and addresses a question I&#x27;ve had about LoRA for a while. In a continual learning paper from last year, I found LoRA was extremely effective for faster fine-tuning and not forgetting the original dataset: https://arxiv.org/abs/2306.01904</p><p><a href="https://hackerpaper.kaipfister.de/p/2306.01904/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV