T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformersby Mariano V. Ntrougkas, Nikolaos…
A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Networkby Ruichen Ma, Guanchao Qiao, Yian Liu, Liwei Meng,…
On the Effectiveness of Distillation in Mitigating Backdoors in Pre-trained Encoderby Tingxu Han, Shenghan Huang,…
Inverse-Free Fast Natural Gradient Descent Method for Deep Learningby Xinwei Ou, Ce Zhu, Xiaolin Huang,…
SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrixby Mrinmay Sen, A. K. Qin, Gayathri C,…
Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Useby Imad Eddine…
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGradby Sayantan Choudhury, Nazarii Tupitsa,…
SGD with Partial Hessian for Deep Neural Networks Optimizationby Ying Sun, Hongwei Yong, Lei ZhangFirst…
NiNformer: A Network in Network Transformer with Token Mixing as a Gating Function Generatorby Abdullah…
DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time Scalingby Qingyuan Wang, Barry Cardiff,…