Ashkan Khakzar

53 papers A* 6Journal 37Unranked 9

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Towards Understanding Multimodal Fine-Tuning: Spatial Features. CoRR Lachin Naghashyar, Hunar Batra, Ashkan Khakzar, Philip Torr, Ronald Clark, Christian Schroeder de Witt, Constantin Venhoff
2025	J	`jnl`	Articulate3D: Zero-Shot Text-Driven 3D Object Posing. CoRR Oishi Deb, Anjun Hu, Ashkan Khakzar, Philip Torr, Christian Rupprecht
2025	J	`jnl`	How Visual Representations Map to Language Feature Space in Multimodal LLMs. CoRR Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda
2025	A*	`conf`	Minimalist Concept Erasure in Generative Models. ICML Yang Zhang, Er Jin, Yanfei Dong, Yixuan Wu, Philip Torr, Ashkan Khakzar, Johannes Stegmaier, Kenji Kawaguchi
2025	J	`jnl`	Minimalist Concept Erasure in Generative Models. CoRR Yang Zhang, Er Jin, Yanfei Dong, Yixuan Wu, Philip Torr, Ashkan Khakzar, Johannes Stegmaier, Kenji Kawaguchi
2025	A*	`conf`	Mixture of Experts Made Intrinsically Interpretable. ICML Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schröder de Witt, Puneet K. Dokania, Adel Bibi, Philip Torr
2025	J	`jnl`	Mixture of Experts Made Intrinsically Interpretable. CoRR Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schröder de Witt, Puneet K. Dokania, Adel Bibi, Philip Torr
2025	J	`jnl`	RelP: Faithful and Efficient Circuit Discovery via Relevance Patching. CoRR Farnoush Rezaei Jafari, Oliver Eberle, Ashkan Khakzar, Neel Nanda
2025	J	`jnl`	Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval. CoRR Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda
2024	J	`jnl`	A Dual-Perspective Approach to Evaluating Feature Attribution Methods. Trans. Mach. Learn. Res. Yawei Li, Yang Zhang, Kenji Kawaguchi, Ashkan Khakzar, Bernd Bischl, Mina Rezaei
2024	J	`jnl`	A Survey on Transferability of Adversarial Examples Across Deep Neural Networks. Trans. Mach. Learn. Res. Jindong Gu, Xiaojun Jia, Pau de Jorge, Wenqian Yu, Xinwei Liu, Avery Ma, Yuan Xun, Anjun Hu, Ashkan Khakzar, Zhijiang Li, Xiaochun Cao, Philip Torr
2024	J	`jnl`	Effortless Efficiency: Low-Cost Pruning of Diffusion Models. CoRR Yang Zhang, Er Jin, Yanfei Dong, Ashkan Khakzar, Philip Torr, Johannes Stegmaier, Kenji Kawaguchi
2024	A*	`conf`	Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models. NeurIPS Arshia Hemmat, Adam Davies, Tom A. Lamb, Jianhao Yuan, Philip Torr, Ashkan Khakzar, Francesco Pinto
2024	J	`jnl`	Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models. CoRR Arshia Hemmat, Adam Davies, Tom A. Lamb, Jianhao Yuan, Philip Torr, Ashkan Khakzar, Francesco Pinto
2024	—	`conf`	Latent Guard: A Safety Framework for Text-to-Image Generation. ECCV (26) Runtao Liu, Ashkan Khakzar, Jindong Gu, Qifeng Chen, Philip Torr, Fabio Pizzati
2024	J	`jnl`	Latent Guard: a Safety Framework for Text-to-image Generation. CoRR Runtao Liu, Ashkan Khakzar, Jindong Gu, Qifeng Chen, Philip Torr, Fabio Pizzati
2024	J	`jnl`	Learning Visual Prompts for Guiding the Attention of Vision Transformers. CoRR Razieh Rezaei, Masoud Jalili Sabet, Jindong Gu, Daniel Rueckert, Philip Torr, Ashkan Khakzar
2024	J	`jnl`	On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions. CoRR Razieh Rezaei, Alireza Dizaji, Ashkan Khakzar, Anees Kazi, Nassir Navab, Daniel Rueckert
2024	J	`jnl`	SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation. CoRR Runtao Liu, Chen I Chieh, Jindong Gu, Jipeng Zhang, Renjie Pi, Qifeng Chen, Philip Torr, Ashkan Khakzar, Fabio Pizzati
2024	J	`jnl`	Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models. CoRR Michael Lan, Philip Torr, Austin Meek, Ashkan Khakzar, David Krueger, Fazl Barez
2024	J	`jnl`	The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms. CoRR Adam Davies, Ashkan Khakzar
2023	J	`jnl`	A Dual-Perspective Approach to Evaluating Feature Attribution Methods. CoRR Yawei Li, Yang Zhang, Kenji Kawaguchi, Ashkan Khakzar, Bernd Bischl, Mina Rezaei
2023	J	`jnl`	A Survey on Transferability of Adversarial Examples across Deep Neural Networks. CoRR Jindong Gu, Xiaojun Jia, Pau de Jorge, Wenqian Yu, Xinwei Liu, Avery Ma, Yuan Xun, Anjun Hu, Ashkan Khakzar, Zhijiang Li, Xiaochun Cao, Philip H. S. Torr
2023	J	`jnl`	AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments. CoRR Yang Zhang, Yawei Li, Hannah Brown, Mina Rezaei, Bernd Bischl, Philip H. S. Torr, Ashkan Khakzar, Kenji Kawaguchi
2023	—	`conf`	FlexR: Few-shot Classification with Language Embeddings for Structured Reporting of Chest X-rays. MIDL Matthias Keicher, Kamilia Zaripova, Tobias Czempiel, Kristina Mach, Ashkan Khakzar, Nassir Navab
2023	—	`conf`	Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images. IPMI Ario Sadafi, Oleksandra Adonkina, Ashkan Khakzar, Peter Lienemann, Rudolf Matthias Hehr, Daniel Rueckert, Nassir Navab, Carsten Marr
2023	J	`jnl`	Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images. CoRR Ario Sadafi, Oleksandra Adonkina, Ashkan Khakzar, Peter Lienemann, Rudolf Matthias Hehr, Daniel Rueckert, Nassir Navab, Carsten Marr
2023	—	`—`	Rethinking Feature Attribution for Neural Network Explanation. Ashkan Khakzar
2022	J	`jnl`	Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models. CoRR Ashkan Khakzar, Yawei Li, Yang Zhang, Mirac Sanisoglu, Seong Tae Kim, Mina Rezaei, Bernd Bischl, Nassir Navab
2022	J	`jnl`	CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN. CoRR Matan Atad, Vitalii Dmytrenko, Yitong Li, Xinyue Zhang, Matthias Keicher, Jan Kirschke, Benedikt Wiestler, Ashkan Khakzar, Nassir Navab
2022	A*	`conf`	Do Explanations Explain? Model Knows Best. CVPR Ashkan Khakzar, Pedram Khorsandi, Rozhin Nobahari, Nassir Navab
2022	J	`jnl`	Do Explanations Explain? Model Knows Best. CoRR Ashkan Khakzar, Pedram Khorsandi, Rozhin Nobahari, Nassir Navab
2022	J	`jnl`	Few-shot Structured Radiology Report Generation Using Natural Language Prompts. CoRR Matthias Keicher, Kamilia Mullakaeva, Tobias Czempiel, Kristina Mach, Ashkan Khakzar, Nassir Navab
2022	—	`conf`	Interpretable Vertebral Fracture Diagnosis. iMIMIC@MICCAI Paul Engstler, Matthias Keicher, David Schinz, Kristina Mach, Alexandra S. Gersing, Sarah C. Foreman, Sophia S. Goller, Juergen Weissinger, Jon Rischewski, Anna-Sophia Dietrich, Benedikt Wiestler, Jan S. Kirschke, Ashkan Khakzar, Nassir Navab
2022	J	`jnl`	Interpretable Vertebral Fracture Diagnosis. CoRR Paul Engstler, Matthias Keicher, David Schinz, Kristina Mach, Alexandra S. Gersing, Sarah C. Foreman, Sophia S. Goller, Juergen Weissinger, Jon Rischewski, Anna-Sophia Dietrich, Benedikt Wiestler, Jan S. Kirschke, Ashkan Khakzar, Nassir Navab
2021	—	`conf`	Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features. MICCAI (3) Ashkan Khakzar, Yang Zhang, Wejdene Mansour, Yuezhi Cai, Yawei Li, Yucheng Zhang, Seong Tae Kim, Nassir Navab
2021	J	`jnl`	Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features. CoRR Ashkan Khakzar, Yang Zhang, Wejdene Mansour, Yuezhi Cai, Yawei Li, Yucheng Zhang, Seong Tae Kim, Nassir Navab
2021	A*	`conf`	Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information. NeurIPS Yang Zhang, Ashkan Khakzar, Yawei Li, Azade Farshad, Seong Tae Kim, Nassir Navab
2021	J	`jnl`	Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information. CoRR Yang Zhang, Ashkan Khakzar, Yawei Li, Azade Farshad, Seong Tae Kim, Nassir Navab
2021	—	`conf`	Longitudinal Quantitative Assessment of COVID-19 Infection Progression from Chest CTs. MICCAI (7) Seong Tae Kim, Leili Goli, Magdalini Paschali, Ashkan Khakzar, Matthias Keicher, Tobias Czempiel, Egon Burian, Rickmer Braren, Nassir Navab, Thomas Wendler
2021	J	`jnl`	Longitudinal Quantitative Assessment of COVID-19 Infection Progression from Chest CTs. CoRR Seong-Tae Kim, Leili Goli, Magdalini Paschali, Ashkan Khakzar, Matthias Keicher, Tobias Czempiel, Egon Burian, Rickmer Braren, Nassir Navab, Thomas Wendler
2021	A*	`conf`	Neural Response Interpretation Through the Lens of Critical Pathways. CVPR Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja, Christian Rupprecht, Seong Tae Kim, Nassir Navab
2021	J	`jnl`	Neural Response Interpretation through the Lens of Critical Pathways. CoRR Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja, Christian Rupprecht, Seong Tae Kim, Nassir Navab
2021	—	`conf`	Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models. MICCAI (3) Ashkan Khakzar, Sabrina Musatian, Jonas Buchberger, Icxel Valeriano Quiroz, Nikolaus Pinger, Soroosh Baselizadeh, Seong Tae Kim, Nassir Navab
2021	J	`jnl`	Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models. CoRR Ashkan Khakzar, Sabrina Musatian, Jonas Buchberger, Icxel Valeriano Quiroz, Nikolaus Pinger, Soroosh Baselizadeh, Seong Tae Kim, Nassir Navab
2020	J	`jnl`	Rethinking Positive Aggregation and Propagation of Gradients in Gradient-based Saliency Methods. CoRR Ashkan Khakzar, Soroosh Baselizadeh, Nassir Navab
2020	—	`conf`	Spatio-Temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation. BrainLes@MICCAI (1) Stefan Denner, Ashkan Khakzar, Moiz Sajid, Mahdi Saleh, Ziga Spiclin, Seong-Tae Kim, Nassir Navab
2020	J	`jnl`	Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation. CoRR Stefan Denner, Ashkan Khakzar, Moiz Sajid, Mahdi Saleh, Ziga Spiclin, Seong Tae Kim, Nassir Navab
2019	J	`jnl`	Correction to: On the reproducibility of expert-operated and robotic ultrasound acquisitions. Int. J. Comput. Assist. Radiol. Surg. Risto Kojcev, Ashkan Khakzar, Bernhard Fuerst, Oliver Zettinig, Carole Fakhry, Robert DeJong, Jeremy Richmon, Russell H. Taylor, Edoardo Sinibaldi, Nassir Navab
2019	J	`jnl`	Explaining Neural Networks via Perturbing Important Learned Features. CoRR Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja, Seong Tae Kim, Nassir Navab
2019	—	`conf`	Learning Interpretable Features via Adversarially Robust Optimization. MICCAI (6) Ashkan Khakzar, Shadi Albarqouni, Nassir Navab
2019	J	`jnl`	Learning Interpretable Features via Adversarially Robust Optimization. CoRR Ashkan Khakzar, Shadi Albarqouni, Nassir Navab
2017	J	`jnl`	On the reproducibility of expert-operated and robotic ultrasound acquisitions. Int. J. Comput. Assist. Radiol. Surg. Risto Kojcev, Ashkan Khakzar, Bernhard Fuerst, Oliver Zettinig, Carole Fahkry, Robert DeJong, Jeremy D. Richmon, Russell H. Taylor, Edoardo Sinibaldi, Nassir Navab