Manos Zaranis
@ManosZaranis
PhD student @istecnico | 2020 Alumni ECE NTUA
🚨Meet MF²: Movie Facts & Fibs: a new benchmark for long-movie understanding! 🤔Do you think your model understands movies? Unlike existing benchmarks, MF² targets memorable events, emotional arcs 💔, and causal chains 🔗 — things humans recall easily, but even top models like…
The second, even better and bigger model is now out: EuroLLM-9B 🇪🇺 Ranks as the best open EU-made LLM of its size, proving competitive or superior when going up against models like Meta's Llama 3.1, Qwen 2.5, and Google's Gemma-2. Blog post & models: lnkd.in/d9JJvmd7
EuroLLM Multilingual Language Models for Europe The quality of open-weight LLMs has seen significant improvement, yet they remain predominantly focused on English. In this paper, we introduce the EuroLLM project, aimed at developing a suite of open-weight multilingual LLMs…
🚀 Big news! Tower+ is here — our strongest open-weight multilingual model yet!
🚀 Tower+: our latest model in the Tower family — sets a new standard for open-weight multilingual models! We show how to go beyond sentence-level translation, striking a balance between translation quality and general multilingual capabilities. 1/5 arxiv.org/pdf/2506.17080
Check out TREQA! TL;DR: We evaluate translation quality of complex content through QA using LLMs.
MT metrics excel at evaluating sentence translations, but struggle with complex texts We introduce *TREQA* a framework to assess how translations preserve key info by using LLMs to generate & answer questions about them arxiv.org/abs/2504.07583 (co-lead @swetaagrawal20) 1/15
New paper out 🚀 Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models: arxiv.org/abs/2504.01001. We present a framework and release a repository for creating reliable benchmarks for (V)LM tasks quickly and fully automatically.
The position is advertised for 12 months, but it has the possibility of a further 2-year extension
🚀 Postdoc Opportunity! 🚀 With @benbenhh & in collaboration with @inuikentaro, we’re hiring a Postdoc at @sheffieldNLP for Uncertainty Quantification in Foundation Models, with a chance to spend time at RIKEN, Japan! 📅 Deadline: 2 March 🔗 More info: jobs.ac.uk/job/DLS026/res…
🚀 New paper alert! 🚀 Ever tried asking an AI about a 2-hour movie? Yeah… not great. Check: ∞-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation! 🔗 arxiv.org/abs/2501.19098 w/ @tozefarinhas , @mcneural_ , @andre_t_martins
We built the best EU-made LLM of its size! It supports all EU languages (and more), and beats Meta's Llama-3.1 on multilingual benchmarks. Congrats to everyone involved; super proud of this work.
🚀We’re proud to launch EuroLLM, a multilingual model supporting all 24 EU languages! Developed with @istecnico, @EdinburghUni, and @UnivParisSaclay on the MareNostrum supercomputer, its set to be a game changer for AI innovation. 👉Learn more - hubs.li/Q02ZZRkl0