Tue M. Cao
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1
Frequent co-authors
Research Timeline
2026
Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression
The paper introduces a distributional framework using Wasserstein distance to unify the semantic comparison of sparse autoencoder features across different layers and to automatically compress large feature circuits into interpretable supernodes.
Highlighted terms show continued research focus across papers