EU-BRIDGE aimed at developing automatic transcription and translation technology that permits the development of innovative multimedia captioning and translation services of audiovisual documents between European and non-European languages. The project provided streaming technology that can convert speech from lectures, meetings, and telephone conversations into the text in another language. Therefore EU-BRIDGE intends to put together academics, engineering and business expertise in order to create competitive offers to existing needs of translation, communication, content processing and publishing. The four use cases were: Captioning Translation for TV broadcasts, University Lecture Translations, European Parliament Translations, Unified Communication Translation. The prospective users of the project were European companies operating in an audiovisual market (in particular TV captioning and translation).
🤔 What Matters in Data for DPO? I asked myself this question a few days ago while trying to understand how to generate a dataset with preferences to run #DPO. This recent #NeurIPS paper answered some of my questions. The findings are simple but crucial for data creation:
🎓 Come and join our group! 🎓
We offer 2 fully funded PhD positions:
🌍 Human-Centred Evaluation Frameworks for Multilingual Technologies (A6)
🤖 Multimedia Personalization with Multimodal Large Language Models (A7)
⏰ Deadline: 15 May 2026
🔗 Details: https://iecs.unitn.it/education/admission/call-for-application
Our pick of the week by
@FBKZhihangXie
: "Detecting Hallucination in SpeechLLMs at Inference Time Using Attention Maps" by @JWaldendorf, Bashar Awwad Shiekh Hasan and Evgenii Tsymbalov
📰
#SpeechLLM #Hallucination
🚀 New paper: Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps
📄 http://arxiv.org/abs/2604.19565
🧩 Lightweight inference-time detection for SpeechLLM hallucinations via audio attention.
✨ Attention classifiers beat uncertainty baselines on ASR and S2TT.
🚀 New Shared Task: Model Compression for Machine Translation at #WMT2026 (co-located with #EMNLP2026)!
📅 Test data out on June 18th, submissions by July 2nd!
Can you shrink an LLM and keep translation quality high? 🧠🔧
👉 https://www2.statmt.org/wmt26/model-compression.html #NLP #ML #LLM #ModelCompression