Jannis Vamvas, PhD
Language AI Researcher at University of Zurich
Recent posts
Just Released: Machine Translation Engine for Romansh
Covering the six varieties of the Romansh language.
Read post
OpenAI's Speculative Decoding,
Reverse-Engineered
Why LLMs are faster if we give them a draft to complete.
Read postRecent publications
Apertus Team. 2026. Apertus 1.5: From Open Text Models to Open Multimodal Reasoners. Pre-print. [cite] [model]
Vilém Zouhar, Niyati Bafna, Mukund Choudhary, Maike Züfle, Sara Rajaee, Pinzhen Chen, Jannis Vamvas, and 237 others. 2026. Last Translation Benchmark. Pre-print. [cite] [data] [code]
Jannis Vamvas, Ignacio Pérez Prat, Angela Heldstab, Dominic P. Fischer, Sina Ahmadi and Rico Sennrich. 2026. Translation Asymmetry in LLMs as a Data Augmentation Factor: A Case Study for 6 Romansh Language Varieties. Accepted to Findings of EMNLP 2026. [cite] [data] [model] [code]
Michelle Wastl, Jannis Vamvas and Rico Sennrich. 2026. Scaling Unsupervised Word Alignment to Documents via Structural Constraints. Accepted to EMNLP 2026. [cite] [data] [code, code]
Hanxu Hu, Zdeněk Šnajdr, Pinzhen Chen, Jannis Vamvas and Rico Sennrich. 2026. Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation. Accepted to Findings of EMNLP 2026. [cite] [code]
Recent teaching
| Fall 2026 | Lecturer Fundamentals of Large Language Models |
| Fall 2026 | Lecturer Mathematical Foundations for Language Technology 1 |
| Fall 2026 | Co-instructor Ethics of AI for Language and Speech |
| Spring 2026 | Lecturer CAS Generative AI |
| Spring 2026 | Lecturer Text Generation with Language Models |