Authors

Ya-Wei Eileen Lin

Publications 2

Preprint Open access

How Do Transformers Learn to Represent Symmetries?

Eduardo Santos-Escriche, Valerie Engelmayer, Ya-Wei Eileen Lin et al. · 2026

Training Transformer-based architectures with finite data augmentation has become an increasingly popular approach in geometric machine learning. Despite its empirical success, the interplay between the Transformer architecture, invariance to different symmetries, and augmentation budgets remains underexplored. In this …

Preprint Open access

Training-Free Transformer Merging via Sequential Local Operator Alignment

Akansh Maurya, Ya-Wei Eileen Lin, Stefanie Jegelka et al. · 2026

Training-free model merging aims to combine multiple fine-tuned models into a single model without further optimization on labeled data. Yet, in transformers, independently merging individual layers can affect a shared attention computation because the query-key and value-output operators depend on composed matrices, o …

Co-authors