JUMAS addresses the need to build an infrastructure able to optimise the information workflow in order to facilitate later analysis. New models and techniques for representing and automatically extracting the embedded semantics derived from multiple data sources will be developed. The most important goal of the JUMAS system is to collect, enrich and share multimedia documents annotated with embedded semantic minimising manual transcription activity. JUMAS is tailored at managing situations in which multiple cameras and audio sources are used to record assemblies in which people debates and event sequences need to be semantically reconstructed for future consultations. The prototype of JUMAS will be tested interworking with legacy systems, but the system can be viewed as able to support business processes and problem-solving in a variety of domains.
Our pick of the week by @beomseok_lee_: "ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs" by Pooneh Mousavi, @yingzhi_wang, @mirco_ravanelli, and @CemSubakan (2025)
#SLU #speech #multimodal #LLM
Speech-language models show promise in multimodal tasksโbut how well are speech & text actually aligned? ๐ค
This paper https://arxiv.org/abs/2505.19937 proposes a new metric to measure layer-wise correlation between the two, with a focus on SLU tasks. ๐๐ฃ๏ธ๐
๐ Ciao! Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio!
๐https://bocconi.eu.qualtrics.com/jfe/form/SV_2nTelXaXvJlinbg (รจ anonimo, dura ~10 m, se partecipi o lo diffondi ci aiuti un sacco๐)
Ci interessa anche raggiungere persone che non si occupano di AI!
Our pick of the week by @apierg: "Agree to Disagree? A Meta-Evaluation of LLM Misgendering" by Arjun Subramonian, Vagrant Gautam, Preethi Seshadri, Dietrich Klakow, @kaiwei_chang, @YizhouSun (2025).
#LLM #misgendering #gender
Super interesting paper by Subramonian et al: "Agree to Disagree? A Meta-Evaluation of LLM Misgendering" https://arxiv.org/abs/2504.17075
Turns out, misgendering is messier than just pronouns. I'd love to see this analysis extended to grammatical gender languages! #LLM #AI #ethics @fbk_mt
๐ New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in ๐ฌ๐ง English and ๐ฎ๐น Italian.
The models are live and ready to try on @huggingface ๐
๐
#ASR #ST #OpenScience #MultilingualAI