This work reveals that the recent Muon optimizer as a mechanism that regulates this factor by construction tightens the interference bound for both CL and MM, positioning Muon as a principled optimizer-centric approach complementary to existing solutions.
Shan Liu, Yuehan Yin, Yinghuan Shi et al.· 0 citations
This paper first proves that TFS is a sufficient condition for weight disentanglement, and finds that TFS also gives rise to an observable geometric consequence: weight vector orthogonality, which positions TFS as the common cause for both the desired functional outcome and a measurable geometric property.
Shan Liu, Yuehan Yin, Lei Wang et al.· arXiv.org· 3 citations
Harness Continual Learning is formulated, a new continual learning paradigm in which the harness evolves around a frozen foundation model, and the resulting loss of earlier behavior as harness-level forgetting is defined.
Borui Kang, Jinrui Gu, Junhan Lv et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.