Kronecker-preconditioned optimizers recompute a cached curvature eigendecomposition only periodically, and implementations and adaptive methods control this through the refresh frequency. We show that frequency leaves part of a schedule free: at a fixed number of refreshes, when they occur changes held-out loss at the...
Xin-Yu Wang, Zhi-Wei Zhai, Yu Gu et al.· 0 citations
Biomedical language models (LMs) provide strong representations for clinical tasks, but they often fail to capture the hierarchical structure among medical concepts. This limitation is especially pronounced for rare and fine-grained clinical codes in long-tailed vocabularies, where hierarchy-agnostic LM representations...
Zi-Yang Song, Li Shen, Yi-Xuan Li et al.· 0 citations
Language models (LMs) offer strong textual representations for electronic health records (EHRs), but they encode patient sequences in isolation and provide limited explainability. Graph neural networks (GNNs) complement LMs by incorporating inter-patient relationships and enabling reference-patient attribution, yet the...
Xin-Yu Wang, Yi-Xuan Li, Han-Wei Wu et al.· 0 citations
DoctorAgents is proposed, an agentic AI framework that autonomously constructs and optimizes end-to-end ML pipelines through specialized large language model (LLM) agents for generation, validation, and refinement.
Ruilin Wang, Bo-Hong Wang, Elizabeth Kourbatski et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
