Deep Learning
Error Correction Code Transformer
We encode each channel's output dimension to a high dimension for better representation of the bits' information to be processed separately.
Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups
We show the universality of depth-2 group convolutional neural networks (GC-NNs) in a unified and constructive manner based on the ridgelet theory.
Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups
We show the universality of depth-2 group convolutional neural networks (GC-NNs) in a unified and constructive manner based on the ridgelet theory.
Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules
This yields continuous-time counterparts of Fast Weight Programmers and linear Transformers.
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
We also empirically demonstrate that the knowledge of large ViTPose models can be easily transferred to small ones via a simple knowledge token.
Exploring Length Generalization in Large Language Models Cem Anil 1, 3, Yuhuai Wu
However, in these domains, the number of available problems typically drops rapidly as a function of problem length (e.g. Figure 2).
Differentiable Convex Optimization Layers
Akshay Agrawal, Brandon Amos, Shane Barratt, Stephen Boyd, Steven Diamond, J. Zico Kolter
Neural Information Processing Systems http://nips.cc/
A Closer Look at AUROC and AUPRC under Class Imbalance
Prompted by these insights, we reviewed over 1.5 million scientific papers to understand the origin of this invalid