Uncategorized

Luisa Bentivogli at Interspeech2026 in Sydney 🇦🇺

by Luca Corbucci | Oct 13, 2026 | News, Uncategorized | 0

Three papers co-authored by researchers from the MT Unit were presented at Interspeech 2026, the...

3 Papers Accepted at CLiC-it 2026 2026

by Luca Corbucci | Aug 5, 2026 | News, Uncategorized | 0

We are happy to announce that 3 papers, co-authored by our Machine Translation Group, have been...

Luisa Bentivogli at ACL 2026 🇺🇸

by Luca Corbucci | Jul 1, 2026 | News, Uncategorized | 0

The Machine Translation unit is heading to the ACL 2026 Conference in San Diego, California! Luisa...

3 Papers Accepted at INTERSPEECH 2026

by Luca Corbucci | Jun 11, 2026 | News, Uncategorized | 0

We’re glad to share that the three papers, co-authored by our Machine Translation Group at FBK,...

MT Unit at LREC 2026 🏝️

by Luca Corbucci | May 11, 2026 | News, Uncategorized | 0

The MT Unit is heading to LREC 2026 in Palma de Mallorca (May 11–16)! Lina Conti and Luisa...

Sara Papi at ICLR 𝟮𝟬𝟮𝟲 🇧🇷

by Luca Corbucci | Apr 22, 2026 | News, Uncategorized | 0

We are happy to announce that Sara Papi is attending ICLR 2026 in Rio de Janeiro, Brazil 🇧🇷. She...

Hello world!

by admin | May 10, 2023 | Uncategorized | 0

Welcome to WordPress. This is your first post. Edit or delete it, then start writing!

MT Group at FBK Follow

#MachineTranslation Research Unit @FBK_research. #nlproc #deeplearning #ai

Avatar

Can LLM Agents Learn how to behave According to your preferences?

PersonaAgent is a framework that combines personalized memory and tool use to help LLM agents adapt their actions to individual users without fine-tuning the underlying model.

Reply on Twitter 2110731059856032025 Retweet on Twitter 2110731059856032025 Like on Twitter 2110731059856032025 2 Twitter 2110731059856032025

Avatar

MT Group at FBK

@fbk_mt ·

7 Oct

Our #PickOfTheWeek, selected by @mgaido91: "Alignment Is All You Need: Instruction-Free Training for General Audio-Language Models" by Xuanru Zhou, Yiwen Shao, Jiahong Li, and Dong Yu 🎧

Can instruction-free training power the next generation of audio-language models?

Marco Gaido @mgaido91

Cool to see we are not the only ones working on building SpeechLLMs with instruction-following capabilities without requiring LLM adaptation and instruction-following data that is expensive to collect!
https://arxiv.org/abs/2608.18132

@fbk_mt

Reply on Twitter 2107769752903204903 Retweet on Twitter 2107769752903204903 Like on Twitter 2107769752903204903 4 Twitter 2107769752903204903

Avatar

MT Group at FBK

@fbk_mt ·

21 Sep

Our #PickOfTheWeek, selected by @BeatriceSavoldi:

"The AI Observatory: A Public Measure of Real-World AI Use" by @ShayneRedford, @AnkaReuel, @zoeykii et al.

A crucial framework tracking how AI models are deployed, adopted, and evaluated beyond lab benchmarks.

BeatriceSavoldi @BeatriceSavoldi

Pick of the week @fbk_mt
📚"The AI Observatory: A Public Measure of Real-World AI Use"

A study and taxonomy to explore real conversations across multiple datasets.
https://www.dataprovenance.org/ai_observatory.pdf

Reply on Twitter 2101969420931182729 Retweet on Twitter 2101969420931182729 Like on Twitter 2101969420931182729 7 Twitter 2101969420931182729

Avatar

MT Group at FBK

@fbk_mt ·

9 Sep

Can algorithmic gender prediction ever be valid?

Check out this week's top pick by @lina_conti: "Algorithmic Gender Prediction Is Illegitimate, But Gender Imputation Can Yield Valid Measurements" by @evandongyx & @ang3linawang.

Lina Conti @lina_conti

Pick of the week by @evandongyx & @ang3linawang:
https://arxiv.org/pdf/2608.13444

Predicting gender from images or names can reveal discrimination. But the practice itself harms trans people. This paper works through when that tradeoff might be justified and how to do it responsibly.

Reply on Twitter 2097788909849567426 Retweet on Twitter 2097788909849567426 Like on Twitter 2097788909849567426 1 Twitter 2097788909849567426