Roberto Dessi
11 papers · 2018–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (37) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🧭
Keyword Pioneer
🧬
Topic Evolution
📈
Trend Setter
❓
The Questioner
(2)
💎
Century Club · Bronze
🗃️
Keyword Collector
(55)
Venues
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(8)
Natural Language Processing
(7)
Deep Learning
(6)
Machine Learning
(6)
Learning Types · Deep Learning
(6)
Learning Types · Machine Learning
(5)
Resources & Methods
(4)
Computer Vision
(3)
Applications
(2)
Architectures
(2)
Generation
(2)
Speech & Audio
(1)
Analysis
(1)
Application Areas
(1)
Keywords
zero-shot learning
(3)
large language model
(3)
self-supervised learning
(3)
language model
(2)
compositional generalization
(2)
emergent communication
(2)
multi-agent system
(2)
prompt engineering
(1)
label smoothing
(1)
information extraction
(1)
visual representation
(1)
image captioning
(1)
distribution shift
(1)
hyperparameter tuning
(1)
in-context learning
(1)
recurrent neural network
(1)
language modeling
(1)
sequence-to-sequence learning
(1)
downstream task
(1)
convolutional neural network
(1)
Papers
Explanations explained. Influence of Free-text Explanations on LLMs and the Role of Implicit Knowledge
EMNLP 2025
Can discrete information extraction prompts generalize across language models?
ICLR 2023
Cross-Domain Image Captioning With Discriminative Finetuning
CVPR 2023
Robustness of Named-Entity Replacements for In-Context Learning
EMNLP 2023
Toolformer: Language Models Can Teach Themselves to Use Tools
NeurIPS 2023
Communication breakdown: On the low mutual intelligibility between human and neural captioning
EMNLP 2022
Emergent Language-Based Coordination In Deep Multi-Agent Systems
EMNLP 2022
Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN
EMNLP 2021
Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
NeurIPS 2021
CNNs found to jump around more skillfully than RNNs: Compositional Generalization in Seq2seq Convolutional Networks
ACL 2019
Fine-tuning on Clean Data for End-to-End Speech Translation: FBK @ IWSLT 2018
EMNLP 2018