AI@TN

Jan 1, 2022 | Projects

1 January 2022 to 31 December 2023 - PROJECT CLOSED

An investment by the Autonomous Province of Trento in young talents involved in projects in synergy between FBK and the University of Trento on common research and highly innovative technological development initiatives that will pave the way for market and societal impact. The research activities will take place in the 4 macro-areas of Integrative AI, AI at the edge, Certified AI, and Interactive AI.

MT Group at FBK Follow

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

Avatar

MT Group at FBK

@fbk_mt ·

Our #PickOfTheWeek 📚: “Training Dynamics Impact Post-Training Quantization Robustness” by @actatjer, @n_ajroldi, @jonasgeiping

Dhairya Suman @dhairya_su47605

Pick of the week @fbk_mt

Cool paper on how robustness to quantization in LLMs is also impacted by training conditions, instead of just the number of training tokens!

https://arxiv.org/abs/2510.06213

Reply on Twitter 2120809833704370449 Retweet on Twitter 2120809833704370449 Like on Twitter 2120809833704370449 1 Twitter 2120809833704370449

Avatar

MT Group at FBK

@fbk_mt ·

21 Oct

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.

Reply on Twitter 2112845795875758101 Retweet on Twitter 2112845795875758101 1 Like on Twitter 2112845795875758101 5 Twitter 2112845795875758101

Avatar

MT Group at FBK

@fbk_mt ·

15 Oct

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 3 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 5 Twitter 2107769752903204903