2 papers
cs.LG2025
FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
Seonglae Cho, Harryn Oh, Donghyun Lee +3
Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025)…
cs.CV2025
Do Your Best and Get Enough Rest for Continual Learning
Hankyul Kang, Gregor Seifer, Donghyun Lee +1
According to the forgetting curve theory, we can enhance memory retention by learning extensive data and taking adequate rest. This means that in order to effectively retain new kn…