Modularity in Transformers: Investigating Neuron Separability & Specializationby Nicholas Pochinkov, Thomas Jones, Mohammed Rashidur RahmanFirst…
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Informationby Diyuan Wu, Ionut-Vlad…
An Empirical Study of Scaling Laws for Transferby Matthew BarnettFirst submitted to arxiv on: 30…
Error-controlled non-additive interaction discovery in machine learning modelsby Winston Chen, Yifan Jiang, William Stafford Noble,…
HLogformer: A Hierarchical Transformer for Representing Log Databy Zhichao Hou, Mina Ghashami, Mikhail Kuznetsov, MohamadAli…
On-device AI: Quantization-aware Training of Transformers in Time-Seriesby Tianheng Ling, Gregor SchieleFirst submitted to arxiv…
Large-Scale Multi-omic Biosequence Transformers for Modeling Peptide-Nucleotide Interactionsby Sully F. Chen, Robert J. Steele, Beakal…
TCNFormer: Temporal Convolutional Network Former for Short-Term Wind Speed Forecastingby Abid Hasan Zim, Aquib Iqbal,…
Automatic Differential Diagnosis using Transformer-Based Multi-Label Sequence Classificationby Abu Adnan Sadi, Mohammad Ashrafuzzaman Khan, Lubaba…
The Mamba in the Llama: Distilling and Accelerating Hybrid Modelsby Junxiong Wang, Daniele Paliotta, Avner…