2 papers
cs.LG2026
LC-SEPLM: long-range contact-supervised adaptation for sequence-only protein representation learning
Chen Wang, Boming Kang, Qinghua Cui
Protein language models learn transferable sequence representations. However, because they primarily model contextual dependencies along amino-acid sequences, their training object…
cs.LG2024
Ratio law: mathematical descriptions for a universal relationship between AI performance and input samples
Boming Kang, Qinghua Cui
Artificial intelligence based on machine learning and deep learning has made significant advances in various fields such as protein structure prediction and climate modeling. Howev…