| Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization S Bombari, MH Amani, M Mondelli Advances in Neural Information Processing Systems (NeurIPS), 2022, 2022 | 48 | 2022 |
| Apertus: Democratizing open and compliant llms for global language environments A Hernández-Cano, A Hägele, A Hao Huang, A Romanou, AJ Solergibert, ... arXiv e-prints, arXiv: 2509.14233, 2025 | 6 | 2025 |
| RL for Reasoning by Adaptively Revealing Rationales MH Amani, A Lotfi, NM Baldwin, S Bengio, M Farajtabar, E Abbe, R West arXiv preprint arXiv:2506.18110, 2025 | 4 | 2025 |
| Symbolic autoencoding for self-supervised sequence learning MH Amani, NM Baldwin, A Mansouri, M Josifoski, M Peyrard, R West ICML 2024 workshop on Differentiable Almost Everything, 2024 | 2 | 2024 |
| Apertus: Democratizing Open and Compliant LLMs for Global Language Environments P Apertus, A Hernández-Cano, A Hägele, AH Huang, A Romanou, ... arXiv preprint arXiv:2509.14233, 2025 | | 2025 |
| Sharp asymptotics on the compression of two-layer neural networks MH Amani, S Bombari, M Mondelli, R Pukdee, S Rini Information Theory Workshop (ITW), 2022, 2022 | | 2022 |
| Symbolic Autoencoding with Straight-Through Gradient Approximations MH Amani, N Baldwin, A Mansouri, M Josifoski, M Peyrard, R West | | |
Marco MondelliProfessor, IST AustriaVerified email at ist.ac.at
