The main objectives of the ECHO (European Chronicles on-Line) project are to develop a long-term reusable software infrastructure to support digital film archives, to provide Web-based access to collections of historical documentary films of great international value and to increase the productivity and cost effectiveness of producing digital film archives. The project develops and demonstrates an open architecture approach to distributed digital film archive services. The open architecture will support service extensibility and interoperability. The distinct features of the ECHO system will be semi-automatic metadata extraction and acquisition from digital film information, non-English speech recognizers (Italian, French, Dutch) for the purpose of indexing, searching and retrieval, cross-language retrieval capabilities, intelligent access to digital films, automatic film summary creation, collection mechanisms, privacy and billing mechanisms.
🤔 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