A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...

[ICLR 2023] The official code for our ICLR 2023 (top25%) paper: "Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning"

[NeurIPS 2022] The official code for our NeurIPS 2022 paper "Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?".

The official code for our paper "Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants".

Codebase for arXiv:2405.17767, based on GPT-Neo and TinyStories.

[CVPR 2023] The official code for our CVPR 2023 paper "Understanding Imbalanced Semantic Segmentation Through Neural Collapse".

[NeurIPS 2023] Official implementation of "A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks"

Official implementation of "Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap" (HUG). [ICLR 2023]

Exploring "variability collapse" in shallow neural networks

Code for "Memorization-Dilation: Modeling Neural Collapse under Noise" as published at ICLR 2023.