Publications

Aleksandar Petrov, Shruti Agarwal, Philip H.S. Torr, Adel Bibi, John Collomosse (2025). On the Coexistence and Ensembling of Watermarks. Neural Information Processing Systems (NeurIPS25).

PDF

Andrew M Bean, Ryan Othniel Kearns, Angelika Romanou, Franziska Sofia Hafner, Harry Mayne, Jan Batzner, Negar Foroutan, Chris Schmitz, Karolina Korgul, Hunar Batra, Oishi Deb, Emma Beharry, Cornelius Emde, Thomas Foster, Anna Gausen, María Grandury, Simeng Han, Valentin Hofmann, Lujain Ibrahim, Hazel Kim, Hannah Rose Kirk, Fangru Lin, Gabrielle Kaili-May Liu, Lennart Luettgau, Jabez Magomere, Jonathan Rystrøm, Anna Sotnikova, Yushi Yang, Yilun Zhao, Adel Bibi, Antoine Bosselut, Ronald Clark, Arman Cohan, Jakob Foerster, Yarin Gal, Scott A Hale, Inioluwa Deborah Raji, Christopher Summerfield, Philip HS Torr, Cozmin Ududec, Luc Rocher, Adam Mahdi (2025). Measuring what Matters: Construct Validity in Large Language Model Benchmarks. Neural Information Processing Systems (NeurIPS25).

PDF Dataset Project

Lukas Aichberger, Alasdair Paren, Guohao Li, Philip H.S. Torr, Yarin Gal, Adel Bibi (2025). Attacking multimodal OS agents with malicious image patches. Neural Information Processing Systems (NeurIPS25).

PDF Project Video

Minseon Kim, Jin Myung Kwak, Lama Alssum, Bernard Ghanem, Philip Torr, David Krueger, Fazl Barez, Adel Bibi (2025). Rethinking Safety in LLM Fine-tuning: An Optimization Perspective. Conference on Laguage Modeling (COLM25).

PDF

Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schroeder de Witt, Puneet K Dokania, Adel Bibi, Philip Torr (2025). Mixture of Experts Made Intrinsically Interpretable. International Conference on Machine Learning (ICML25).

PDF

Cornelius Emde, Francesco Pinto, Thomas Lukasiewicz, Philip H.S. Torr, Adel Bibi (2025). Towards Certification of Uncertainty Calibration under Adversarial Attacks. International Conference on Learning Representations (ICLR25).

PDF

Cornelius Emde, Alasdair Paren, Preetham Arvind, Maxime Kayser, Tom Rainforth, Thomas Lukasiewicz, Bernard Ghanem, Philip H.S. Torr, Adel Bibi (2025). Shh, don't say that! Domain Certification in LLMs. International Conference on Learning Representations (ICLR25).

PDF

Francisco Eiras, Aleksandar Petrov, Philip H.S. Torr, M. Pawan Kumar, Adel Bibi (2025). Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models. International Conference on Learning Representations (ICLR25).

PDF

Wenxuan Zhang, Philip H.S. Torr, Mohamed Elhoseiny, Adel Bibi (2025). Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models. International Conference on Learning Representations (ICLR25) [Spotlight].

PDF Code

Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma, Philip H.S. Torr, Adel Bibi, Samuel Albanie, Matthias Bethge (2024). No "Zero-Shot" Without Exponential Data; Pretraining Concept Frequency Determines Multimodal Model Performance. Neural Information Processing Systems (NeurIPS24).

PDF Code

Ameya Prabhu, Vishaal Udandarao, Philip H.S. Torr, Matthias Bethge, Adel Bibi, Samuel Albanie (2024). Efficient Lifelong Model Evaluation in an Era of Rapid Progress. Neural Information Processing Systems (NeurIPS24).

PDF Code

Botos Csaba, Wenxuan Zhang, Matthias Müller, Ser-Nam Lim, Mohamed Elhoseiny, Philip H.S. Torr, Adel Bibi (2024). Label Delay in Online Continual Learning. Neural Information Processing Systems (NeurIPS24).

PDF Code Project

Aleksandar Petrov, Tom A. Lamb, Alasdair Paren, Philip H.S. Torr, Adel Bibi (2024). Universal In-Context Approximation By Prompting Fully Recurrent Models. Neural Information Processing Systems (NeurIPS24).

PDF

Chengxing Xie, Canyu Chen, Feiran Jia, Ziyu Ye, Shiyang Lai, Kai Shu, Jindong Gu, Adel Bibi, Ziniu Hu, David Jurgens, James Evans, Philip H.S. Torr, Bernard Ghanem, Guohao Li (2024). Can Large Language Model Agents Simulate Human Trust Behavior?. Neural Information Processing Systems (NeurIPS24).

PDF Code Project Poster

Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati, Philip H.S. Torr, Adel Bibi, Bernard Ghanem, Mete Ozay (2024). Model Merging and Safety Alignment; One Bad Model Spoils the Bunch. Empirical Methods in Natural Language Processing (EMNLP24).

PDF

Hasan Abed Al Kader Hammoud, Tuhin Das, Fabio Pizzati, Philip H.S. Torr, Adel Bibi, Bernard Ghanem (2024). On Pretraining Data Diversity for Self-Supervised Learning. European Conference on Computer Vision (ECCV24).

PDF Code

Kumail Alhamoud, Yasir Ghunaim, Motasem Alfarra, Thomas Hartvigsen, Philip H.S. Torr, Bernard Ghanem, Adel Bibi, Marzyeh Ghassemi (2024). FedMedICL; Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging. The Medical Image Computing and Computer Assisted Intervention Society (MICCAI24).

PDF Code Poster

Aleksandar Petrov, Philip H.S. Torr, Adel Bibi (2024). Prompting a Pretrained Transformer Can Be a Universal Approximator. International Conference on Machine Learning (ICML24).

PDF

Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schroeder, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Botos Csaba, Fabro Steibel, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan Arturo Nolazco Flores, Lori Landay, Matthew T Jackson, Paul Röttger, Philip H.S. Torr, Trevor Darrell, Yong Suk Lee, Jakob Foerster (2024). Near to Mid-term Risks and Opportunities of Open-Source Generative AI. International Conference on Machine Learning (ICML24) [Oral].

PDF

Francisco Eiras, Adel Bibi, Rudy Bunel, Krishnamurthy Dvijotham, Philip H.S. Torr, M. Pawan Kumar (2024). Efficient Error Certification for Physics-Informed Neural Networks. International Conference on Machine Learning (ICML24).

PDF

Yibo Yang, Xiaojie Li, Motasem Alfarra, Hasan Hammoud, Adel Bibi, Philip H.S. Torr, Bernard Ghanem (2024). Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation. International Conference on Machine Learning (ICML24).

PDF

Aleksandra Petrov, Philip H.S. Torr, Adel Bibi (2024). When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations. International Conference on Learning Representations (ICLR24).

PDF Poster

Tim Franzmeyer, Stephen Marcus McAleer, Joao F. Henriques, Jakob Nicolaus Foerster, Philip H.S. Torr, Adel Bibi, Christian Schroeder de Witt (2024). Illusory Attacks: Detectability Matters in Adversarial Attacks on Sequential Decision-Makers. International Conference on Learning Representations (ICLR24) [Spotlight].

PDF Code Project

Wenxuan Zhang, Youssef Mohamed, Bernard Ghanem, Philip H. S. Torr, Adel Bibi, Mohamed Elhoseiny (2024). Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation. International Conference on Learning Representations (ICLR24).

PDF Poster

Motasem Alfarra, Zhipeng Cai, Adel Bibi, Bernard Ghanem, Matthias Müller (2023). SimCS: Simulation for Online Domain-Incremental Continual Segmentation. Association for the Advancement of Artificial Intelligence (AAAI24).

PDF Poster

Alexander Petrov, Emanuele La Malfa, Philip H. S. Torr, Adel Bibi (2023). Language Model Tokenizers Introduce Unfairness Between Languages. Neural Information Processing Systems (NeurIPS23).

PDF Project Poster

Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Gregory Rogéz, Philip H.S. Torr (2023). Catastrophic Overfitting is a Bug but also a Feature. Transactions of Machine Learning Research (TMLR23).

PDF Code

Hasan Abed Al Kader Hammoud, Ameya Prabhu, Ser-Nam Lim, Philip H. S. Torr, Adel Bibi, Bernard Ghanem (2023). Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?. International Conference on Computer Vision (ICCV23).

PDF Code

Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H.S. Torr, Adel Bibi (2023). Certifying Ensembles: A General Certification Theory with S-Lipschitzness. International Conference on Machine Learning (ICML23).

PDF Poster

Hasan Abed Al Kader Hammoud, Adel Bibi, Philip H.S. Torr, Bernard Ghanem (2023). Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs. Workshop on Adversarial Machine Learning on Computer Vision (CVPRW23).

PDF

Yasir Ghunaim, Adel Bibi, Kumail Alhamoud, Motasem Alfarra, Hasan Abed Al Kader Hammoud, Ameya Prabhu, Philip H. S. Torr, Bernard Ghanem (2023). Real-Time Evaluation in Online Continual Learning: A New Hope. Computer Vision and Pattern Recognition (CVPR23) [Highlight].

PDF Code Poster Video

Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet Dokania, Philip H.S. Torr, Ser-Nam Lim, Bernard Ghanem, Adel Bibi (2023). Computationally Budgeted Continual Learning: What Does Matter?. Computer Vision and Pattern Recognition (CVPR23).

PDF Code Poster Video

Taras Rumezhak, Francisco Eiras, Philip H. S. Torr, Adel Bibi (2022). RANCER: Non-Axis Aligned Anisotropic Certification With Randomized Smoothing. Winter Conference on Applications of Computer Vision (WACV23)​.

PDF

Pau de Jorge, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip H. S. Torr, Gregory Rogéz, Puneet K. Dokania (2022). Make Some Noise: Reliable and Efficient Single-Step Adversarial Training. Neural Information Processing Systems (NeurIPS22).

PDF Code

Francisco Eiras, Motasem Alfarra, Philip H.S. Torr, Pawan Kumar, Puneet K. Dokania, Bernard Ghanem, Adel Bibi (2022). ANCER: Anisotropic Certification via Sample-wise Volume Maximization. Transactions of Machine Learning Research (TMLR22).

PDF Code

Motasem Alfarra, Adel Bibi, Hasan Hammoud, Mohamed Gaafar, Bernard Ghanem (2022). On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective. Transactions on Pattern Analysis and Machine Intelligence (TPAMI22).

PDF

Motasem Alfarra, Adel Bibi, Philip H.S. Torr, Bernard Ghanem (2022). Data Dependent Randomized Smoothing. Uncertainty in Artificial Intelligence (UAI22).

PDF Code

Motasem Alfarra, Adel Bibi, Naeemullah Khan, Philip H.S. Torr, Bernard Ghanem (2022). DeformRS: Certifying Input Deformations with Randomized Smoothing. Association for the Advancement of Artificial Intelligence (AAAI22) [Oral].

PDF

Motasem Alfarra, Juan C. Pérez, Ali Thabet, Adel Bibi, Philip H.S. Torr, Bernard Ghanem (2022). Combating Adversaries with Anti-Adversaries. Association for the Advancement of Artificial Intelligence (AAAI22).

PDF Code Slides

Motasem Alfarra, Juan C. Pérez, Adel Bibi, Ali Thabet, Pablo Arbeláez, Bernard Ghanem (2021). ClusTR: Clustering Training for Robustness. British Machine Vision Conference (BMVC21).

PDF Code

Salman Alsubaihi, Adel Bibi, Modar Alfadly, Abdullah Hamdi, Bernard Ghanem (2021). Expected Tight Bounds for Robust Deep Neural Network Training. Robust Machine Learning Workshop at the International Conference on Learning Representations (ICLRW17).

PDF Code

Juan C. Pérez, Motasem Alfarra, Guillaume Jeanneret, Adel Bibi, Ali Thabet, Bernard Ghanem, Pablo Arbeláez (2020). Gabor Layers Enhance Network Robustness. European Conference on Computer Vision (ECCV20).

PDF Code Video

Eduard Gorbunov, Adel Bibi, Ozan Sener, El Houcine Bergou, Peter Richtarik (2020). A Stochastic Derivative Free Optimization Method with Momentum. International Conference on Learning Representation (ICLR20)​.

PDF

Adel Bibi, El Houcine Bergou, Ozan Sener, Bernard Ghanem, Peter Richtarik (2020). A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control. Association for the Advancement of Artificial Intelligence (AAAI20) [Oral].

PDF Poster Slides

Adel Bibi, Bernard Ghanem, Vladlen Koltun, Rene Ranftl (2019). Deep Layers as Stochastic Solvers. International Conference on Learning Representation (ICLR19).

PDF Poster

Rafał Protasiuk, Adel Bibi, Bernard Ghanem (2019). Local Color Mapping Combined with Color Transfer for Underwater Image Enhancement. Winter Conference on Applications of Computer Vision (WACV19)​.

PDF Code Poster Video

Matthias Müller, Adel Bibi, Silvio Giancola, Salman Alsubaihi, Bernard Ghanem (2018). TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild. European Conference on Computer Vision (ECCV18)​.

PDF Code Project Poster Video

Adel Bibi, Modar Alfadly, Bernard Ghanem (2018). Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input. Conference on Computer Vision and Pattern Recognition (CVPR18) [Oral].

PDF Code Poster Slides Video

Adel Bibi, Bernard Ghanem (2017). High Order Tensor Formulation for Convolutional Sparse Coding. International Conference on Computer Vision (ICCV17).

PDF Code Poster

Adel Bibi, Hani Itani, Bernard Ghanem (2017). FFTLasso: Large-Scale Lasso in the Fourier Domain. Computer Vision and Pattern Recognition (CVPR17) [Oral].

PDF Code Poster Slides Video

Adel Bibi, Matthias Müller, Bernard Ghanem (2016). Target Response Adaptation for Correlation Filter Tracking. European Conference on Computer Vision (ECCV16) [Spotlight].

PDF Code Poster Slides Video

Tianzhu Zhang, Adel Bibi, Bernard Ghanem (2016). In Defense of Sparse Tracking: Circulant Sparse Tracker. Conference on Computer Vision and Pattern Recognition (CVPR16) [Spotlight].

PDF Poster Video

Adel Bibi, Tianzhu Zhang, Bernard Ghanem (2016). 3D Part-Based Sparse Tracker with Automatic Synchronization and Registration. Computer Vision and Pattern Recognition (CVPR16).

PDF Poster Video

Adel Bibi, Bernard Ghanem (2016). Multi-Template Scale-Adaptive Kernelized Correlation Filters. International Conference on Computer Vision Workshop (ICCVW15).

PDF Code Poster