Improving Pre-trained Language Model Sensitivity via Mask Specific losses: A case study on Biomedical NERby…
AffineQuant: Affine Transformation Quantization for Large Language Modelsby Yuexiao Ma, Huixia Li, Xiawu Zheng, Feng…
Fisher Mask Nodes for Language Model Mergingby Thennal D K, Ganesh Nathan, Suchithra M SFirst…
SELECTOR: Heterogeneous graph network with convolutional masked autoencoder for multimodal robust prediction of cancer survivalby…
Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftsby Zeyang Zhang, Xin Wang, Ziwei Zhang,…
A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Networkby Ruichen Ma, Guanchao Qiao, Yian Liu, Liwei Meng,…
Masks, Signs, And Learning Rate Rewindingby Advait Gadhikar, Rebekka BurkholzFirst submitted to arxiv on: 29…
Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimizationby Han Guo, Ramtin Hosseini,…
Pretraining Strategy for Neural Potentialsby Zehua Zhang, Zijie Li, Amir Barati FarimaniFirst submitted to arxiv…
Learning to See Through Dazzleby Xiaopeng Peng, Erin F. Fleet, Abbie T. Watnik, Grover A.…