By jointly optimizing distillation and quantization within a unified teacher-anchored framework, this method ensures consistent training under quantization, suppressing hard negatives and enlarging decision margins, and designs a lightweight cross-attention adapter that enhances non-RGB representations through RGB-guid...
Jinwoo Jeon, GyuYeop Do, Yunkyu Lim et al.· 0 citations
LEXIC, a compact recurrent model that predicts response correctness from fixation sequences, word frequency, and character length, has 41.6K parameters and requires no language-model inference, supporting lightweight on-device inference.
Sumin Lee, Kyeonghun Kim, Subeen Lee et al.· 0 citations
A multi-source Masked Autoencoder (MAE) framework, named ProsMAE, for histopathology representation learning, which achieved a higher mean validation quadratic weighted kappa (QWK) than the vanilla MAE frozen linear-probe baseline under the evaluated disjoint PANDA split.
Anna Jung, Kyeonghun Kim, Youngung Han et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.