Publications

Amin Parchami-Araghi, Sukrut Rao, Jonas Fischer, Bernt Schiele. FaCT: Faithful Concept Traces for Explaining Neural Network Decisions. NeurIPS, 2025.

Code

Yifan Wang, Sukrut Rao, Ji-Ung Lee, Mayank Jobanputra, Vera Demberg. B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability. arXiv, 2025.

DOI arXiv Code

Shreyash Arya*, Sukrut Rao*, Moritz Böhle*, Bernt Schiele. B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable. NeurIPS, 2024.

DOI arXiv Code Poster Video Slides

Sukrut Rao*, Sweta Mahajan*, Moritz Böhle, Bernt Schiele. Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV, 2024.

DOI arXiv Paper Code Poster Video Slides

Amin Parchami-Araghi*, Moritz Böhle*, Sukrut Rao*, Bernt Schiele. Good Teachers Explain: Explanation-Enhanced Knowledge Distillation. ECCV, 2024.

DOI arXiv Code Poster Video Slides

Sukrut Rao, Moritz Böhle, Bernt Schiele. Better Understanding Differences in Attribution Methods via Systematic Evaluations. IEEE TPAMI, 2024.

Project DOI arXiv Code Conference Version

Sukrut Rao*, Moritz Böhle*, Amin Parchami-Araghi, Bernt Schiele. Studying How to Efficiently and Effectively Guide Models with Explanations. ICCV, 2023.

Project DOI arXiv Paper Code Poster Video

Sukrut Rao, Moritz Böhle, Bernt Schiele. Towards Better Understanding Attribution Methods. CVPR, 2022.

Project DOI arXiv Paper Code Poster Video Journal Version

Sukrut Rao, David Stutz, Bernt Schiele. Adversarial Training against Location-Optimized Adversarial Patches. ECCV-W, 2020.

Project DOI arXiv Paper Code Slides Video

Saurabh Joshi, Prateek Kumar, Sukrut Rao, Ruben Martins. Open-WBO-Inc: Approximation Strategies for Incomplete Weighted MaxSAT. JSAT, 2019.

Project DOI Paper Code Conference Version

Saurabh Joshi, Prateek Kumar, Ruben Martins, Sukrut Rao. Approximation Strategies for Incomplete MaxSAT. CP, 2018.

Project DOI arXiv Paper Code Slides Journal Version

Vaibhav B Sinha, Sukrut Rao, Vineeth N Balasubramanian. Fast Dawid-Skene: A Fast Vote Aggregation Scheme for Sentiment Classification. KDD WISDOM, 2018.

Project DOI arXiv Paper Code Slides Web Page