Yixuan Duan
Yixuan Duan has 1 paper in the ChatPPG research atlas (2026) and 1 co-author in the atlas. Main topics: ECG, interpretability, sparse-autoencoder, mechanistic-interp, benchmark, preprint.
Papers
- ECG-InterpBench: Benchmarking Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders2026 · arXiv preprint
ECG-InterpBench measures how interpretable the learned representations inside ECG foundation models are, alongside how well they predict. It uses sparse autoencoders of matched capacity as standard measuring tools. The authors tested six frozen ECG foundation models across five encoder depths, five dictionary widths and three seeds, producing a 450-cell interpretability atlas.
- Published: arXiv preprint, 2026
- Signals: ECG
- Method: capacity-matched sparse autoencoders