Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
Paper
•
2510.25480
•
Published
Florian
hlzlhlzl
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
4 days ago
LlamaFusion: Adapting Pretrained Language Models for Multimodal
Generation
upvoted
an
article
9 days ago
nanoVLM: The simplest repository to train your VLM in pure PyTorch
authored
a paper
3 months ago
Gradient-Weight Alignment as a Train-Time Proxy for Generalization in
Classification Tasks
Organizations
authored
a
paper
3 months ago
authored
a
paper
5 months ago