Author

T. M. Cao

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence May 2026

Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression

This work introduces a distributional framework for SAE analyses, in which each feature is represented not by a single decoder vector like in the literature, but by an activation-weighted distribution over the hidden states that express it, and provides a unified semantic metric for cross-layer feature comparison.

T. M. Cao, D. Nguyen, My T. Thai · arXiv.org · 2 citations

#machine learning Preprint Sep 2026

Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space

Activation space and parameter space provide complementary views of model computation. Activations represent information, while weights read, transform, and write that information. Yet existing interpretability methods largely study the two spaces separately, leaving the connection between represented information and p...

T. M. Cao, Lisiane Pruinelli, My T. Thai · 0 citations