Get started
Author

Roberto Dessì

Toolformer: Language Models Can Teach Themselves to Use Tools
2023 · Timo Schick, Jane Dwivedi-Yu, et al. · neural information processing systems · 1,087
PDF
Augmented Language Models: a Survey
2023 · Mialon, Grégoire, Dessì, Roberto, et al. · arXiv (Cornell University) · 160
PDF
Enhancing Transformer for End-to-end Speech-to-Text Translation
2019 · Mattia Antonino Di Gangi, Matteo Negri, et al. · 48
Cross-Domain Image Captioning with Discriminative Finetuning
2023 · Roberto Dessì, Michele Bevilacqua, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 22
PDF
Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN
2021 · Rahma Chaabouni, Roberto Dessì, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · 15
PDF
CNNs found to jump around more skillfully than RNNs: Compositional Generalization in Seq2seq Convolutional Networks
2019 · Roberto Dessì, Marco Baroni · Annual Meeting of the Association for Computational Linguistics (ACL) · 11
PDF
Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
2021 · Dessì, Roberto, Kharitonov, Eugene, et al. · arXiv (Cornell University) · 8
PDF
Computer-Aided Design of Multi-Agent Cyber-Physical Systems
2018 · J. Sini, M. Violante, et al. · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · 8
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018
2018 · Di Gangi, Mattia Antonino, Dessì, Roberto, et al. · arXiv (Cornell University) · 7
PDF
Emergent Language-Based Coordination In Deep Multi-Agent Systems
2022 · Marco Baroni, Roberto Dessi, et al. · 6
PDF
Time Heals All (Shallow) Wounds: A Lesson on Forgiveness of Ingroup Transgressors Learned by the Feyenoord Vandal Fans
2017 · Marika Rullo, Fabio Presaghi, et al. · Social Sciences · 4
PDF
Robustness of Named-Entity Replacements for In-Context Learning
2023 · Saeed Goodarzi, Nikhil Kagita, et al. · 3
PDF
Communication breakdown: On the low mutual intelligibility between human and neural captioning
2022 · Roberto Dessì, Eleonora Gualdoni, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 3
PDF
Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game
2019 · Dessì, Roberto, Bouchacourt, Diane, et al. · arXiv (Cornell University) · 3
PDF
Description of a collaborative sperm whale birth and shifts in coda vocal styles during key events
2026 · Yaniv Aluma, Zethra Baron, et al. · Scientific Reports · 1
PDF
Generative AI collective behavior needs an interactionist paradigm
2026 · Ferrarotti, Laura, Campedelli, Gian Maria, et al. · arXiv (Cornell University) · 1
PDF
Can discrete information extraction prompts generalize across language models?
2023 · Rakotonirina, Nathanaël Carraz, Dessì, Roberto, et al. · Repositori digital de la UPF (Universitat Pompeu Fabra) · 1
OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations
2026 · Mustun, Faadil, Semenzin, Chiara, et al. · arXiv (Cornell University)
PDF
MoGround: Measuring and Mitigating Modality Distraction in Vision-Language Models
2026 · Zhou, Luca, Zhao, Bo, et al. · arXiv (Cornell University)
PDF
The Undetected Damage of Quantization on Retrieval and How to Fix It
2026 · Zhou, Luca, Zirilli, Alessandro, et al. · arXiv (Cornell University)
PDF
Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation
2026 · Zhou, Luca, Shah, Sajel, et al. · arXiv (Cornell University)
PDF
Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations
2026 · Semenzin, Chiara, Mustun, Faadil, et al. · arXiv (Cornell University)
PDF
Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models
2025 · Marincione, Davide, Crisostomi, Donato, et al. · arXiv (Cornell University)
PDF
Explanations explained. Influence of Free-text Explanations on LLMs and the Role of Implicit Knowledge
2025 · Andrea Zaninello, Roberto Dessi, et al. · Joint Conference on Lexical and Computational Semantics
PDF
I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
2024 · Campedelli, Gian Maria, Penzo, Nicolò, et al. · arXiv (Cornell University)
PDF
Works count: 27
Citation count: 1,381
H-index: 8
I10-index: 6
Year
Topic
Type