pith. sign in

Su-In Lee

Identifiers

  • name variant Su-In Lee 0.60 · backfill

Papers (14)

  1. A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders cs.LG · 2026 · author #3
  2. Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution cs.MA · 2026 · author #4
  3. Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment cs.LG · 2026 · author #3
  4. SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models cs.LG · 2026 · author #5
  5. Explainable AI for Trees: From Local Explanations to Global Understanding cs.LG · 2019 · author #10
  6. Consistent Individualized Feature Attribution for Tree Ensembles cs.LG · 2018 · author #3
  7. Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data cs.LG · 2018 · author #3
  8. Anesthesiologist-level forecasting of hypoxemia with only SpO2 data using deep learning cs.LG · 2017 · author #4
  9. Checkpoint Ensembles: Ensemble Methods from a Single Training Process cs.LG · 2017 · author #3
  10. Consistent feature attribution for tree ensembles cs.AI · 2017 · author #2
  11. A Unified Approach to Interpreting Model Predictions cs.AI · 2017 · author #2
  12. An unexpected unity among methods for interpreting model predictions cs.AI · 2016 · author #2
  13. Learning Graphical Models With Hubs stat.ML · 2014 · author #4
  14. Node-Based Learning of Multiple Gaussian Graphical Models stat.ML · 2013 · author #5

Mentions

  • 2606.07007 #3 · arxiv_oai · confidence 0.70 Su-In Lee
  • 2601.22276 #5 · arxiv_oai · confidence 0.70 Su-In Lee
  • 1402.7349 #4 · backfill · confidence 0.70 Su-In Lee
  • 2605.27621 #4 · arxiv_oai · confidence 0.70 Su-In Lee
  • 1303.5145 #5 · backfill · confidence 0.70 Su-In Lee

Frequent Coauthors