publications
* denotes equal contribution.
2024
- A Dual-Perspective Approach to Evaluating Feature Attribution MethodsTransactions on Machine Learning Research (TMLR), 2024
- FinerCut: Finer-grained Interpretable Layer Pruning for Large Language ModelsCompression Workshop at NeurIPS 2024, 2024
- Probabilistic Self-supervised Representation Learning via Scoring Rules MinimizationIn The Twelfth International Conference on Learning Representations (ICLR), 2024
2023
- AttributionLab: Faithfulness of Feature Attribution Under Controllable EnvironmentsNeurIPS 2023 Workshop XAI in Action, 2023
2022
- Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the ModelsICML Workshop on Interpretable Machine Learning in Healthcare, 2022
- Deep learning-based classification of dermatological lesions given a limited amount of labelled dataJournal of the European Academy of Dermatology and Venereology, 2022
2021
- Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive InformationAdvances in Neural Information Processing Systems (NeurIPS), 2021
- Explaining covid-19 and thoracic pathology model predictions by identifying informative input featuresIn International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021
2019
- Logistic Regression with Robust BootstrappingIn 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2019