| Optimizer benchmarking needs to account for hyperparameter tuning PT Sivaprasad, F Mai, T Vogels, M Jaggi, F Fleuret International conference on machine learning, 9036-9045, 2020 | 66* | 2020 |
| Bq-nco: Bisimulation quotienting for efficient neural combinatorial optimization D Drakulic, S Michel, F Mai, A Sors, JM Andreoli Advances in Neural Information Processing Systems 36, 77416-77429, 2023 | 62* | 2023 |
| Using deep learning for title-based semantic subject indexing to reach competitive performance to full-text F Mai, L Galke, A Scherp Proceedings of the 18th ACM/IEEE on joint conference on digital libraries …, 2018 | 46 | 2018 |
| Using titles vs. full-text as source for automated semantic document annotation L Galke, F Mai, A Schelten, D Brunsch, A Scherp Proceedings of the 9th Knowledge Capture Conference, 1-4, 2017 | 36* | 2017 |
| Plug and play autoencoders for conditional text generation F Mai, N Pappas, I Montero, NA Smith, J Henderson arXiv preprint arXiv:2010.02983, 2020 | 35 | 2020 |
| Multi-modal adversarial autoencoders for recommendations of citations and subject labels L Galke, F Mai, I Vagliano, A Scherp Proceedings of the 26th conference on user modeling, adaptation and …, 2018 | 30 | 2018 |
| Hypermixer: An mlp-based low cost alternative to transformers F Mai, A Pannatier, F Fehr, H Chen, F Marelli, F Fleuret, J Henderson arXiv preprint arXiv:2203.03691, 2022 | 20* | 2022 |
| CBOW is not all you need: Combining CBOW with the compositional matrix space model F Mai, L Galke, A Scherp arXiv preprint arXiv:1902.06423, 2019 | 18 | 2019 |
| Hyperconformer: Multi-head hypermixer for efficient speech recognition F Mai, J Zuluaga-Gomez, T Parcollet, P Motlicek arXiv preprint arXiv:2305.18281, 2023 | 16 | 2023 |
| Open-source conversational ai with speechbrain 1.0 M Ravanelli, T Parcollet, A Moumen, S de Langen, C Subakan, ... Journal of Machine Learning Research 25 (333), 1-11, 2024 | 14 | 2024 |
| Learning to plan for language modeling from unlabeled data N Cornille, MF Moens, F Mai arXiv preprint arXiv:2404.00614, 2024 | 7 | 2024 |
| Using adversarial autoencoders for multi-modal automatic playlist continuation I Vagliano, L Galke, F Mai, A Scherp Proceedings of the ACM Recommender Systems Challenge 2018, 1-6, 2018 | 7 | 2018 |
| Bag-of-vectors autoencoders for unsupervised conditional text generation F Mai, J Henderson arXiv preprint arXiv:2110.07002, 2021 | 4 | 2021 |
| Learning entailment-based sentence embeddings from natural language inference RK Mahabadi, F Mai, J Henderson | 3 | 2019 |
| Natural language understanding A Castle, MF Moens, M Trusca, F Mai, J Sun | 2 | 1989 |
| Reranking-based recommender system with deep learning A Saleh, F Mai, C Nishioka, A Scherp INFORMATIK 2017, 2169-2175, 2017 | 1 | 2017 |
| Improving Language Modeling by Increasing Test-time Planning Compute F Mai, N Cornille, MF Moens Eighth Widening NLP Workshop (WiNLP 2024) Phase II, 0 | 1 | |
| End-to-end Planner Training for Language Modeling N Cornille, F Mai, J Sun, MF Moens arXiv preprint arXiv:2410.12492, 2024 | | 2024 |
| Learning to Plan Long-Term for Language Modeling F Mai, N Cornille, MF Moens arXiv preprint arXiv:2409.00070, 2024 | | 2024 |
| Triple-Encoders: Representations That Fire Together, Wire Together JJ Erker, F Mai, N Reimers, G Spanakis, I Gurevych arXiv preprint arXiv:2402.12332, 2024 | | 2024 |
Ansgar ScherpUniversity of Ulm, GermanyVerified email at ansgarscherp.net
