Roberto Dessì

29 papers A* 5A 1Journal 17Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Generative AI collective behavior needs an interactionist paradigm. CoRR Laura Ferrarotti, Gian Maria Campedelli, Roberto Dessì, Andrea Baronchelli, Giovanni Iacca, Kathleen M. Carley, Alex Pentland, Joel Z. Leibo, James Evans, Bruno Lepri
2025	J	`jnl`	I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy. Trans. Mach. Learn. Res. Gian Maria Campedelli, Nicolò Penzo, Massimo Stefan, Roberto Dessì, Marco Guerini, Bruno Lepri, Jacopo Staiano
2025	J	`jnl`	Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models. CoRR Davide Marincione, Donato Crisostomi, Roberto Dessì, Emanuele Rodolà, Emanuele Rossi
2025	J	`jnl`	Referential communication in heterogeneous communities of pre-trained visual deep networks. Trans. Mach. Learn. Res. Matéo Mahaut, Roberto Dessì, Francesca Franzon, Marco Baroni
2024	J	`jnl`	I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy. CoRR Gian Maria Campedelli, Nicolò Penzo, Massimo Stefan, Roberto Dessì, Marco Guerini, Bruno Lepri, Jacopo Staiano
2023	J	`jnl`	Augmented Language Models: a Survey. CoRR Grégoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ramakanth Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, Edouard Grave, Yann LeCun, Thomas Scialom
2023	J	`jnl`	Augmented Language Models: a Survey. Trans. Mach. Learn. Res. Grégoire Mialon, Roberto Dessì, Maria Lomeli, Christoforos Nalmpantis, Ramakanth Pasunuru, Roberta Raileanu, Baptiste Rozière, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, Edouard Grave, Yann LeCun, Thomas Scialom
2023	A*	`conf`	Can discrete information extraction prompts generalize across language models? ICLR Nathanaël Carraz Rakotonirina, Roberto Dessì, Fabio Petroni, Sebastian Riedel, Marco Baroni
2023	J	`jnl`	Can discrete information extraction prompts generalize across language models? CoRR Nathanaël Carraz Rakotonirina, Roberto Dessì, Fabio Petroni, Sebastian Riedel, Marco Baroni
2023	A*	`conf`	Cross-Domain Image Captioning with Discriminative Finetuning. CVPR Roberto Dessì, Michele Bevilacqua, Eleonora Gualdoni, Nathanaël Carraz Rakotonirina, Francesca Franzon, Marco Baroni
2023	J	`jnl`	Cross-Domain Image Captioning with Discriminative Finetuning. CoRR Roberto Dessì, Michele Bevilacqua, Eleonora Gualdoni, Nathanaël Carraz Rakotonirina, Francesca Franzon, Marco Baroni
2023	A	`conf`	Referential Communication in Heterogeneous Communities of Pre-trained Visual Deep Networks. AAMAS Matéo Mahaut, Francesca Franzon, Roberto Dessì, Marco Baroni
2023	J	`jnl`	Referential communication in heterogeneous communities of pre-trained visual deep networks. CoRR Matéo Mahaut, Francesca Franzon, Roberto Dessì, Marco Baroni
2023	—	`conf`	Robustness of Named-Entity Replacements for In-Context Learning. EMNLP (Findings) Saeed Goodarzi, Nikhil Kagita, Dennis Minn, Shufan Wang, Roberto Dessì, Shubham Toshniwal, Adina Williams, Jack Lanchantin, Koustuv Sinha
2023	A*	`conf`	Toolformer: Language Models Can Teach Themselves to Use Tools. NeurIPS Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, Thomas Scialom
2023	J	`jnl`	Toolformer: Language Models Can Teach Themselves to Use Tools. CoRR Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, Thomas Scialom
2022	A*	`conf`	Communication breakdown: On the low mutual intelligibility between human and neural captioning. EMNLP Roberto Dessì, Eleonora Gualdoni, Francesca Franzon, Gemma Boleda, Marco Baroni
2022	J	`jnl`	Communication breakdown: On the low mutual intelligibility between human and neural captioning. CoRR Roberto Dessì, Eleonora Gualdoni, Francesca Franzon, Gemma Boleda, Marco Baroni
2022	—	`conf`	Emergent Language-Based Coordination In Deep Multi-Agent Systems. EMNLP (Tutorial Abstracts) Marco Baroni, Roberto Dessì, Angeliki Lazaridou
2021	—	`conf`	Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN. BlackboxNLP@EMNLP Rahma Chaabouni, Roberto Dessì, Eugene Kharitonov
2021	J	`jnl`	Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN. CoRR Rahma Chaabouni, Roberto Dessì, Eugene Kharitonov
2021	A*	`conf`	Interpretable agent communication from scratch (with a generic visual processor emerging on the side). NeurIPS Roberto Dessì, Eugene Kharitonov, Marco Baroni
2021	J	`jnl`	Interpretable agent communication from scratch(with a generic visual processor emerging on the side). CoRR Roberto Dessì, Eugene Kharitonov, Marco Baroni
2019	—	`conf`	CNNs found to jump around more skillfully than RNNs: Compositional Generalization in Seq2seq Convolutional Networks. ACL (1) Roberto Dessì, Marco Baroni
2019	J	`jnl`	CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks. CoRR Roberto Dessì, Marco Baroni
2019	—	`conf`	Enhancing Transformer for End-to-end Speech-to-Text Translation. MTSummit (1) Mattia Antonino Di Gangi, Matteo Negri, Roldano Cattoni, Roberto Dessì, Marco Turchi
2019	J	`jnl`	Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game. CoRR Roberto Dessì, Diane Bouchacourt, Davide Crepaldi, Marco Baroni
2018	—	`conf`	Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018. IWSLT Mattia Antonino Di Gangi, Roberto Dessì, Roldano Cattoni, Matteo Negri, Marco Turchi
2018	J	`jnl`	Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018. CoRR Mattia Antonino Di Gangi, Roberto Dessì, Roldano Cattoni, Matteo Negri, Marco Turchi