Testoni, Alberto
Testoni, Alberto
A Small but Informed and Diverse Model: The Case of the Multimodal GuessWhat!? Guessing Game
2022-01-01 Greco, Claudio; Testoni, Alberto; Bernardi, Raffaella; Frank, Stella
ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments
2022-01-01 Hanna, Michael; Pedeni, Federico; Testoni, Alberto; Suglia, Alessandro; Bernardi, Raffaella
Artificial Intelligence models do not ground negation, humans do. GuessWhat?! dialogues as a case study
2022-01-01 Testoni, Alberto; Greco, Claudio; Bernardi, Raffaella
Asking Strategic and Informative Questions in Visual Dialogue Games: Strengths and Weaknesses of Neural Generative Models
2023-02-24 Testoni, Alberto
Boosting Questions' Effectiveness in Medical Interviews
2024-01-01 Mazzaccara, Davide; Testoni, Alberto; Bernardi, Raffaella
Garbage In, Flowers Out: Noisy Training Data Help Generative Models at Test Time
2022-01-01 Testoni, Alberto; Bernardi, Raffaella
Grounding Dialogue History: Strengths and Weaknesses of Pre-trained Transformers
2021-01-01 Greco, Claudio; Testoni, Alberto; Bernardi, Raffaella
Jointly learning to see, ask, decide when to stop, and then GuessWhat
2019-01-01 Shekhar, Ravi; Testoni, Alberto; Fernández, Raquel; Bernardi, Raffaella
Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain
In corso di stampa Mazzaccara, Davide; Testoni, Alberto; Bernardi, Raffaella
Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy
2021-01-01 Testoni, Alberto; Bernardi, Raffaella
Overprotective Training Environments Fall Short at Testing Time: Let Models Contribute to Their Own Training
2020-01-01 Testoni, Alberto; Bernardi, Raffaella
Probability Distributions as a Litmus Test to Inspect NNs Grounding Skills
2022-01-01 Lucassen, A. J.; Testoni, A.; Bernardi, Raffaella
Quantifiers in a MultimodalWorld: Hallucinating Vision with Language and Sound
2019-01-01 Testoni, Alberto; Pezzelle, Sandro; Bernardi, Raffaella
The Devil is in the Detail: A Magnifying Glass for the GuessWhich Visual Dialogue Game
2019-01-01 Testoni, Alberto; Shekhar, Ravi; Fernández, Raquel; Bernardi, Raffaella
The Efficiency of Question-Asking Strategies in a Real-World Visual Search Task
2023-01-01 Testoni, A.; Bernardi, R.; Ruggeri, A.
The Interplay of Task Success and Dialogue Quality: An in-depth Evaluation in Task-Oriented Visual Dialogues
2021-01-01 Testoni, Alberto; Bernardi, Raffaella
They Are Not All Alike: Answering Different Spatial Questions Requires Different Grounding Strategies
2020-01-01 Testoni, Alberto; Greco, Claudio; Bianchi, Tobias; Mazuecos, Mauricio; Marcante, Agata; Benotti, Luciana; Bernardi, Raffaella
Visually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History
2021-01-01 Dong, Tianai; Testoni, Alberto; Benotti, Luciana; Bernardi, Raffaella
Which Turn do Neural Models Exploit the Most to Solve GuessWhat? Diving into the Dialogue History Encoding in Transformers and LSTMs
2020-01-01 Greco, Claudio; Testoni, Alberto; Bernardi, Raffaella
“I’ve Seen Things You People Wouldn’t Believe”: Hallucinating Entities in GuessWhat?!
2021-01-01 Testoni, Alberto; Bernardi, Raffaella