Jannis Vamvas
@j_vamvas
Natural Language Processing (#NLProc) Researcher at University of Zurich @cl_uzh
Past: PhD @UZH_en, intern @amazon, alumnus @CisLmu
ID: 342387054
https://www.vamvas.ch/ 25-07-2011 22:59:55
212 Tweet
646 Followers
485 Following
Excited for tomorrow to present our work on LLM response stability in the context of political bias assessment at Conference on Language Modeling! Stop by between 9 and 11 at poster #39. Joint work w/Jannis Vamvas and Lena Jäger. 🔗 openreview.net/pdf?id=7xUtka9…
Join my lab! I’m currently recruiting new students (MSc & PhD) for admission in the fall of 2025 at Mila - Institut québécois d'IA mila.quebec/en/prospective… Are you interested in multilingual NLP? I would encourage you to apply. Deadline: December 1
Congratulations to Michelle Wastl on receiving an UZH Semester Award for her Master's thesis, «Unsupervised Translation Direction Detection», completed under the supervision of Professor Rico Sennrich.
I'm thrilled to share my first PhD project, a joint work with Jannis Vamvas and Rico Sennrich. Paper link: arxiv.org/pdf/2503.10494 Long context LLMs have paved the way for document translation, but is simply inputting the whole content the optimal way? Here's the thread 🧵 [1/n]
![I'm thrilled to share my first PhD project, a joint work with <a href="/j_vamvas/">Jannis Vamvas</a> and <a href="/RicoSennrich/">Rico Sennrich</a>.
Paper link:
arxiv.org/pdf/2503.10494
Long context LLMs have paved the way for document translation, but is simply inputting the whole content the optimal way?
Here's the thread 🧵 [1/n]](https://pbs.twimg.com/media/GmAiR8uWoAE_4jJ.jpg "Hanxu Hu (@huhanxu1) on Twitter photo I'm thrilled to share my first PhD project, a joint work with <a href=\"/j_vamvas/\">Jannis Vamvas</a> and <a href=\"/RicoSennrich/\">Rico Sennrich</a>.
Paper link:
arxiv.org/pdf/2503.10494
Long context LLMs have paved the way for document translation, but is simply inputting the whole content the optimal way?
Here's the thread 🧵 [1/n]")
University of Zurich and Huawei researchers explore how #LLMs can improve document-level 📄 #AI #translation by preserving context across segments 🔁 and integrating additional knowledge layers 💡 University of Zurich Universität Zürich Zurich Computational Linguistics Group Hanxu Hu Jannis Vamvas Rico Sennrich slator.com/how-large-lang…
