| Revisiting Character-level Adversarial Attacks for Language Models E Abad Rocamora, Y Wu, F Liu, G Chrysos, V Cevher International Conference on Machine Learning (ICML), 2024 | 9* | 2024 |
| Efficient local linearity regularization to overcome catastrophic overfitting EA Rocamora, F Liu, GG Chrysos, PM Olmos, V Cevher International Conference on Learning Representations (ICLR), 2024 | 6 | 2024 |
| Sound and Complete Verification of Polynomial Networks E Abad Rocamora, MF Sahin, F Liu, G Chrysos, V Cevher Neural Information Processing Systems (NeurIPS), 2022 | 6 | 2022 |
| Membership Inference Attacks against Large Vision-Language Models Z Li, Y Wu, Y Chen, F Tonin, EA Rocamora, V Cevher Neural Information Processing Systems (NeurIPS), 2024 | 1 | 2024 |
| Certified Robustness Under Bounded Levenshtein Distance E Abad Rocamora, GG Chrysos, V Cevher International Conference on Learning Representations (ICLR), 2025 | | 2025 |
| Learning task-specific features for 3D pointcloud graph creation E Abad-Rocamora, J Ruiz-Hidalgo arXiv preprint arXiv:2209.00949, 2022 | | 2022 |
| LION: A bidirectional framework that trains like a Transformer and infers like an RNN A Afzal, EA Rocamora, LN Candogan, P Puigdemont, F Tonin, Y Wu, ... | | |
| Single-pass detection of jailbreaking input in large language models LN Candogan, Y Wu, EA Rocamora, G Chrysos, V Cevher ICLR 2024 Workshop on Secure and Trustworthy Large Language Models, 0 | | |
Volkan CevherAssociate Professor, LIONS, EPFL. Amazon Scholar (AGI Foundations).確認したメール アドレス: epfl.ch