| 2025 | EMNLP | FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data. | Thibaut Thonet, Germn Kruszewski, Jos Rozen, Pierre Erbacher, Marc Dymetman |
| 2024 | ICLR | Compositional Preference Models for Aligning LMs. | Dongyoung Go, Tomasz Korbak, Germn Kruszewski, Jos Rozen, Marc Dymetman |
| 2023 | ACL | Should you marginalize over possible tokenizations? | Nadezhda Chirkova, Germn Kruszewski, Jos Rozen, Marc Dymetman |
| 2023 | ACL | disco: a toolkit for Distributional Control of Generative Models. | Germn Kruszewski, Jos Rozen, Marc Dymetman |
| 2023 | ICML | Aligning Language Models with Preferences through f-divergence Minimization. | Dongyoung Go, Tomasz Korbak, Germn Kruszewski, Jos Rozen, Nahyeon Ryu, Marc Dymetman |
| 2022 | ICML | Controlling Conditional Language Models without Catastrophic Forgetting. | Tomasz Korbak, Hady Elsahar, Germn Kruszewski, Marc Dymetman |
| 2019 | NAACL | Cooperative Learning of Disjoint Syntax and Semantics. | Serhii Havrylov, Germn Kruszewski, Armand Joulin |
| 2019 | NAACL | The emergence of number and syntax units in LSTM language models. | Yair Lakretz, Germn Kruszewski, Theo Desbordes, Dieuwke Hupkes, Stanislas Dehaene, Marco Baroni |
| 2018 | ACL | What you can cram into a single \$&!#* vector: Probing sentence embeddings for linguistic properties. | Alexis Conneau, Germn Kruszewski, Guillaume Lample, Loc Barrault, Marco Baroni |
| 2017 | ICLR | CommAI: Evaluating the first steps towards a useful general AI. | Marco Baroni, Armand Joulin, Allan Jabri, Germn Kruszewski, Angeliki Lazaridou, Klemen Simonic, Toms Mikolov |
| 2016 | ACL | The LAMBADA dataset: Word prediction requiring a broad discourse context. | Denis Paperno, Germn Kruszewski, Angeliki Lazaridou, Quan Ngoc Pham, Raffaella Bernardi, Sandro Pezzelle, Marco Baroni, Gemma Boleda, Raquel Fernndez |
| 2016 | EMNLP | Convolutional Neural Network Language Models. | Ngoc-Quan Pham, Germn Kruszewski, Gemma Boleda |
| 2015 | ACL | Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model. | Nghia The Pham, Germn Kruszewski, Angeliki Lazaridou, Marco Baroni |
| 2015 | NAACL | So similar and yet incompatible: Toward the automated identification of semantically compatible words. | Germn Kruszewski, Marco Baroni |
| 2014 | ACL | Don't count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors. | Marco Baroni, Georgiana Dinu, Germn Kruszewski |
| 2012 | INLG | Generation for Grammar Engineering. | Claire Gardent, Germn Kruszewski |