arXiv AI
From the Loss Landscape to Diverse Feature Learning in Neural Networks
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 4
Understanding Machine Unlearning Through the Lens of Mode Connectivity
arXiv:2504. 06407v2 Announce Type: replace Abstract: Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch.
arXiv AI
Jul 28
Understanding Machine Unlearning Through the Lens of Mode Connectivity
arXiv:2607. 23970v1 Announce Type: cross Abstract: Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch.
arXiv Machine Learning
Sep 10
Feature Superposition in Neural Networks: From Theory to Practice
arXiv:2609.06862v1 Announce Type: new Abstract: Superposition refers to neural networks representing more features than they have dimensions. It offers a possible explanation for polysemantic neurons...
Hugging Face Trending Papers
Jul 27
Understanding Machine Unlearning Through the Lens of Mode Connectivity
Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch. Despite recent progress, the loss landscape and optimization geometry of unlearning are poorly understood.
arXiv Machine Learning
Sep 22
Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity
arXiv:2609.24379v1 Announce Type: cross Abstract: Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entan...
arXiv Machine Learning
Sep 1
Mode Connectivity Beyond Classifiers: Evidence from Generative and Contrastive Models
arXiv:2608.30366v1 Announce Type: new Abstract: The loss landscape of Deep Neural Networks (DNNs) exhibits highly complex and non-convex properties. Recent studies have revealed the phenomenon of mod...