A neural-anchor-based retrieval framework that treats the high-repetition center as an anchor and approaches it from both sides: a denoiser pulls the noisy query toward the true anchor, and a small network predicts each candidate's pseudo anchor from its image and pulls the image toward it.
Zhenyao Cui, Siyuan Kan, Ding-Kun Liu et al.· 0 citations
The results indicate that: 1) linear probing is frequently insufficient; 2) specialist models trained from scratch remain competitive across many tasks; and 3) larger FMs do not necessarily yield better generalization performance under current data regimes and training practices.
Dingkun Liu, Yu-Heng Chen, Zhu Chen et al.· National Science Review· 12 citations· ⚡3
STEAM is presented, a hierarchical transfer framework that reconciles general-purpose representation learning with paradigm-specific specialization in EEG foundation models and attains the best average rank among the compared methods at a competitive inference cost measured in FLOPs.
Zhu Chen, Dingkun Liu, Yu-Heng Chen et al.· 0 citations
Shrinkage-Whitened Proxy Cross-Entropy (SW-ProxyCE), a query-free task-aware attack framework that recovers task-level decision geometry from a small labeled reference set through shrinkage-whitened class prototypes, enabling transferable adversarial generation without training an additional surrogate classifier is pro...
Linhua Cong, Dingkun Liu, Dongrui Wu· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
