2 papers
cs.LG2026
Scalable and Interpretable Representation Alignment with Ordinal Similarity
Diogo Soares, Pankhil Gawade, Andrea Dittadi +1
Evaluating representation similarity is fundamental to representation learning. However, existing metrics suffer from significant limitations: they lack interpretability due to shi…
q-bio.QM2026
FoldSAE: Learning to Steer Protein Folding Through Sparse Representations
Wojciech Zarzecki, Paulina Szymczak, Ewa Szczurek +1
RFdiffusion is a popular and well-established model for generation of protein structures. However, this generative process offers limited insight into its internal representations…