iiinova — where your digital self keeps evolving

Reposted by Jannis Vamvas

The Last Translation Benchmark is still open (10 accepted submissions in any language/dialect for coauthorship 🤩). last-translation-benchmark.vilda.net Also submit your model & try to beat LTB. We added all the latest models: North Small Translate (@cohere.com), Mistral Large 4, Qwen 3.8, congrats!

092

Jannis Vamvas @vamvas.bsky.social · 07/09/2026

Eine deutsche KI behauptet, Schweizerdeutsch zu können. Unser neuer Test sagt: «Chabis». vamvas.ch/benchmark-sw...

vamvas.ch

Eine deutsche KI behauptet, Schweizerdeutsch zu können. Unser neuer Test sagt: «Chabis»

152

Reposted by Jannis Vamvas

Inside IT @inside-it.ch · 28/04/2026

Das Institut für Computerlinguistik der Universität Zürich hat mit der Lia Rumantscha ein Sprachmodell für die rätoromanischen Sprachvarianten entwickelt.

inside-it.ch

Sprachmodell übersetzt in fünf rätoromanische Idiome

Das Programm "Alas" übersetzt Deutsch ins Rätoromanische. Es kann als Webapp und Open-Source-Modell benutzt werden.

083

Reposted by Jannis Vamvas

Computational Linguistics @ UZH @cl-uzh.bsky.social · 28/04/2026

Only a few more days left to register for SwissText 2026 with early-bird rates!

001

Reposted by Jannis Vamvas

Computational Linguistics @ UZH @cl-uzh.bsky.social · 10/04/2026

Looking forward to the ACL 2026 conference in San Diego, California! Several accepted papers have involvement from our department: 1/7

🔵 Michelle Wastl, Jannis Vamvas, Rico Sennrich. SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents.

🔵 Zifan Jiang, Youngjoon Jang, Liliane Momeni, Gül Varol, Sarah Ebling, Andrew Zisserman. Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing.

🔵 Kevin Du, Clara Kümpel, Michelle Wastl, Alex Warstadt. It’s Not What You Say, It’s How You Say It: Evaluating LLM Responses to Expressions of Belief.

🔵 Negar Foroutan, Clara Meister, Debjit Paul, Joel Niklaus, Sina Ahmadi, Antoine Bosselut, Rico Sennrich. Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization.

🔵 Apertus: Democratizing Open and Compliant LLMs for Global Language Environments. https://lnkd.in/eFTh-5m7

🔵 (Findings:) Elias Schuhmacher, Andrianos Michail, Juri Opitz, Rico Sennrich, Simon Clematide. Information Representation Fairness in Long-Document Embeddings: The Peculiar Interaction of Positional and Language Bias.

153

Reposted by Jannis Vamvas

Rico Sennrich @ricosennrich.bsky.social · 23/03/2026

My lab is recruiting one PhD student and one post-doctoral researcher for a start as soon as this Summer! Apply by April 1 / March 31 to be among first candidates considered. jobs.uzh.ch/job-vacancie... jobs.uzh.ch/job-vacancie...

jobs.uzh.ch

UZH: PhD in Language AI / Natural Language Processing

You will be joining the Department of Computational Linguistics, which has 6 Research Groups and around 70 postdoctoral and student researchers in the areas of Text Technologies, Phonetics and Speech ...

046

Reposted by Jannis Vamvas

Computational Linguistics @ UZH @cl-uzh.bsky.social · 09/02/2026

📣 SwissText 2026 – Call for Papers is open! 🎯 Special theme: #ReproducibleNLP 📅 Submission deadline: 17 March 2026 📍 Zurich, Switzerland · 10 June 2026 www.swisstext.org/call-for-pap... (1/4)

swisstext.org

2026 Call for Papers | SwissText

163

Reposted by Jannis Vamvas

Hanxu Hu @hanxuhu.bsky.social · 21/10/2025

💥Introducing new paper: arxiv.org/pdf/2510.17715, QueST — train specialized generators to create challenging coding problems. From Qwen3-8B-Base ✅ 100K synthetic problems: better than Qwen3-8B ✅ Combining with human written problems: matches DeepSeek-R1-671B 🧵(1/5)

143

Reposted by Jannis Vamvas

Computational Linguistics @ UZH @cl-uzh.bsky.social · 30/07/2025

Congratulations to @sinaahmadi.bsky.social and co-authors for receiving an ACL 2025 Outstanding Paper Award for PARME: Parallel Corpora for Low-Resourced Middle Eastern Languages! aclanthology.org/2025.acl-lon...

0156

Reposted by Jannis Vamvas

Computational Linguistics @ UZH @cl-uzh.bsky.social · 29/07/2025

We're proud to see our researchers sharing their latest work: @sinaahmadi.bsky.social, @ricosennrich.bsky.social, @michellewastl.bsky.social, @vamvas.bsky.social and Andrianos Michail (pictured) and many others. If you’re at #ACL, stop by to learn more!

Sina Ahmadi, Rico Sennrich, Michelle Wastl, Jannis Vamvas, Andrianos Michail from the Department of Computational Linguistics posing in front of the at ACL 2025 Vienna step-and-repeat banner

0174

Reposted by Jannis Vamvas

michellewastl.bsky.social @michellewastl.bsky.social · 26/07/2025

Arrived in Vienna ready for #ACL2025NLP! Excited to present papers with @vamvas.bsky.social @ricosennrich.bsky.social on Unsupervised Translation Direction Detection and Multilingual Hallucination Detection! Come say hi! 👋 #NLProc #NLP #NMT #LLMs

172

Jannis Vamvas @vamvas.bsky.social · 23/06/2025

Can you solve my exam question? I've come to believe that multiple-choice exams are underrated. More in my blog post, “The Joy of Multiple-Choice.” vamvas.ch/the-joy-of-m...

Make a guess: How does GPT-4o tokenize the Lithuanian word ‘nebeprisikiškiakopūsteliautum’?
A. ⟨nebepr, is, ik, iškiak, opūste, liautum⟩
B. ⟨neb, pre, ski, kayak, opus, tell, autumn⟩
C. ⟨ne, be, pris, iki, ški, ak, op, ū, stel, ia, utum⟩

040

Reposted by Jannis Vamvas

michellewastl.bsky.social @michellewastl.bsky.social · 19/05/2025

I had the pleasure of presenting our paper “20min-XD: A Comparable Corpus of Swiss News Articles (arxiv.org/abs/2504.21677) ”, a joint work with @vamvas.bsky.social , Selena Calleri and @ricosennrich.bsky.social , at SwissText 2025 last week. We are honored to receive Best Paper Award for it! ✨

093

Reposted by Jannis Vamvas

Computational Linguistics @ UZH @cl-uzh.bsky.social · 13/05/2025

Our Michelle Wastl is demonstrating her invention, the Translation Direction Detector, at the SwissNLP Expo! Michelle's paper: arxiv.org/abs/2401.06769 Demo: huggingface.co/spaces/Zuric... If you're at the expo, make sure to stop by the Department of Computational Linguistics UZH!

063

Jannis Vamvas @vamvas.bsky.social · 21/04/2025

I also found what others complained about previously: The “Predicted Outputs” feature is unstable even with temp=0. It’s unclear to me why this happens – do they batch the verification steps of users? An artifact of temperature sampling? So, any hints would be appreciated! 4/4

Bar chart illustrating counts of different API responses for the same request.

010

Jannis Vamvas @vamvas.bsky.social · 21/04/2025

Systematic probing of the OpenAI API reveals that they are using a lookahead parameter of K=16, and perform prefix matching with a prefix threshold of 32 tokens. A simulation experiment confirms that the reverse-engineered algorithm matches the behavior of the API. 3/4

3D plot comparing API behavior to simulation results.

100

Jannis Vamvas @vamvas.bsky.social · 21/04/2025

Draft verification is a well-known idea in NLP, from Speculative Decoding to algorithms leveraging a static draft, such as Aggressive Decoding and Prompt Lookup Decoding. Clearly, “Predicted Outputs” does something similar. But how does it work, specifically? 2/4

Schematic illustration of draft verification

100

Jannis Vamvas @vamvas.bsky.social · 21/04/2025

OpenAI introduced the “Predicted Outputs” feature last November, but their documentation raises more questions than it answers. So let’s reverse-engineer the feature! 🧵1/4 platform.openai.com/docs/guides/...

platform.openai.com

OpenAI Platform

Explore developer resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's platform.

100

Jannis Vamvas @vamvas.bsky.social · 21/04/2025

Blogged: Reverse-engineering OpenAI's Speculative Decoding. I was curious how GPT-4o can make use of predicted outputs to speed up text generation. vamvas.ch/openai-predi...

vamvas.ch

OpenAI's Speculative Decoding, Reverse-Engineered

Why LLMs are faster if we give them a draft to complete.

160

Reposted by Jannis Vamvas

Computational Linguistics @ UZH @cl-uzh.bsky.social · 11/04/2025

Congratulations to Dr. @shaitarova.bsky.social , who just successfully defended her thesis on "Generated Text as the Locus of Language Contact: Exploring the Impact of Generative AI on English and German". Special thanks to the external examiner Natalia Resende!

2123

Reposted by Jannis Vamvas

Hanxu Hu @hanxuhu.bsky.social · 14/03/2025

I'm thrilled to share my first PhD project, a joint work with @vamvas.bsky.social and @ricosennrich.bsky.social 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]

183

Reposted by Jannis Vamvas

Rico Sennrich @ricosennrich.bsky.social · 06/12/2024

Congratulations to Dr. @tannonk.bsky.social, who just successfully defended his thesis on "Leveraging Data, Decoding, and Context for Controlling Text Generation from Pretrained Language Models". Special thanks to the external examiner @feralvam.bsky.social!

0195

Jannis Vamvas @vamvas.bsky.social · 11/12/2023

Rico Sennrich (University of Zurich) is hiring a PhD student to work on representations of knowledge in multilingual language models, starting September 2024. Rico is my former advisor and I can greatly recommend working with him. Apply by January 4: jobs.uzh.ch/offene-stell...

jobs.uzh.ch

UZH: PhD Student in Natural Language Processing

You will be joining the Department of Computational Linguistics, which has 5 faculties and around 40 postdoctoral and student researchers in the areas of text technologies, phonetics and speech. You w...

041

Jannis Vamvas @vamvas.bsky.social · 03/11/2023

Minimum Bayes Risk decoding has recently gained momentum in #NLProc. However, a generic implementation for @huggingface.bsky.social Transformers has been missing. Check out our new 𝗺𝗯𝗿🔥 repo, which is designed to work with any model and metric on the Hub: github.com/ZurichNLP/mbr

github.com

GitHub - ZurichNLP/mbr: Minimum Bayes Risk Decoding for Hugging Face Transformers

Minimum Bayes Risk Decoding for Hugging Face Transformers - GitHub - ZurichNLP/mbr: Minimum Bayes Risk Decoding for Hugging Face Transformers

000

Jannis Vamvas @vamvas.bsky.social · 19/10/2023

Can NLP be used for highlighting differences between two documents? Our EMNLP paper investigates the task of Recognizing Semantic Differences (RSD) with simple, unsupervised approaches. • Demo: huggingface.co/spaces/Zuric... • Paper: huggingface.co/papers/2305.... #NLProc

huggingface.co

Paper page - Towards Unsupervised Recognition of Semantic Differences in Related Documents

Join the discussion on this paper page

0101