MT Group at FBK (@fbk_mt) header
MT Group at FBK (@fbk_mt) profile picture
Trento, Trentino-South Tyrol
Joined October 2015
Photo by MT Group at FBK (@fbk_mt)Photo by MT Group at FBK (@fbk_mt)Photo by MT Group at FBK (@fbk_mt)Photo by MT Group at FBK (@fbk_mt)Photo by MT Group at FBK (@fbk_mt)Photo by MT Group at FBK (@fbk_mt)Photo by MT Group at FBK (@fbk_mt)Photo by MT Group at FBK (@fbk_mt)Photo by MT Group at FBK (@fbk_mt)Photo by MT Group at FBK (@fbk_mt)
Meet the new PhD additions to our group! 🧑‍💻 Andrea DeCarlo he'll be working on multimedia personalization with multimodal large language models And Harun Eroglu, he'll be working on human-centred evaluation frameworks for multilingual technologies. #MT #NLP #AI #FBK
4
81
Late update but we had two great seminars in October by: 🎤 Alice Ross, a PhD canditate at University of Edinburgh on "Perceived characteristics of synthesised speech in social context"
1
4
100
🎤 Marco A. Stranisci, a PostDoc at IT University, Copenhagen on "Epistemic Injustice in Language Models: an Audit of Pretraining Filters and Guardrails"
41
🛠️ By analyzing optimization hyperparameters and checkpoint evolution, they demonstrate how smoother training dynamics act as an implicit regularizer, yielding models that are naturally more resilient to aggressive weight and activation compression.
1
24
Our #PickOfTheWeek 📚: “High-Fidelity Simultaneous Speech-To-Speech Translation” by @t0m1ab, @lmazare, @EXGRV, @ptrkprz, @honualx and @neilzegh 🎙️➡️🌍 This work shows how a full-duplex SpeechLLM architecture can be adapted for simultaneous S2ST and S2TT.
1
1
5
284
🧩 The authors derive word-level “contextual alignments” from an MT model’s perplexity and enforce them by inserting silences 🤫 or resynthesizing targets with an alignment-aware TTS.
1
76
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.
1
3
132
In this case, personalization goes beyond remembering user information: agents can use past interactions to adapt their reasoning and tool usage. This solution outperforms RAG-based personalization and general-purpose agents across four personalized decision-making tasks.
1
1
52
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?
1
5
128
This paper shows how alignment alone can streamline training and improve real-world evaluation beyond lab benchmarks. #AudioAI #VoiceAI #MachineLearning #LLM #AIResearch
1
37
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.
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. dataprovenance.org/ai_observ…
1
8
231
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.
Pick of the week by @evandongyx & @ang3linawang: 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.
1
2
175