Jannis Vamvas
@vamvas.bsky.social
Natural Language Processing (#NLProc #NLP) Researcher @ University of Zurich @cl-uzh.bsky.social
vamvas.ch
vamvas.ch
Reposted by Jannis Vamvas
💥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)
From Qwen3-8B-Base
✅ 100K synthetic problems: better than Qwen3-8B
✅ Combining with human written problems: matches DeepSeek-R1-671B
🧵(1/5)
October 21, 2025 at 2:01 PM
💥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)
From Qwen3-8B-Base
✅ 100K synthetic problems: better than Qwen3-8B
✅ Combining with human written problems: matches DeepSeek-R1-671B
🧵(1/5)
Reposted by Jannis Vamvas
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...
aclanthology.org/2025.acl-lon...
July 30, 2025 at 3:10 PM
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...
aclanthology.org/2025.acl-lon...
Reposted by Jannis Vamvas
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!
If you’re at #ACL, stop by to learn more!
July 29, 2025 at 1:31 PM
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!
If you’re at #ACL, stop by to learn more!
Reposted by Jannis Vamvas
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
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
July 26, 2025 at 7:33 AM
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
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
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...
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...
June 23, 2025 at 10:39 AM
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...
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...
Reposted by Jannis Vamvas
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! ✨
We are honored to receive Best Paper Award for it! ✨
May 19, 2025 at 10:32 AM
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! ✨
We are honored to receive Best Paper Award for it! ✨
Reposted by Jannis Vamvas
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!
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!
May 13, 2025 at 9:22 AM
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!
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!
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...
I was curious how GPT-4o can make use of predicted outputs to speed up text generation.
vamvas.ch/openai-predi...
OpenAI's Speculative Decoding, Reverse-Engineered
Why LLMs are faster if we give them a draft to complete.
vamvas.ch
April 21, 2025 at 4:52 PM
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...
I was curious how GPT-4o can make use of predicted outputs to speed up text generation.
vamvas.ch/openai-predi...
Reposted by Jannis Vamvas
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!
April 11, 2025 at 9:30 AM
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!
Reposted by Jannis Vamvas
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]
@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]
March 14, 2025 at 2:58 PM
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]
@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]
Reposted by Jannis Vamvas
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!
December 6, 2024 at 10:34 AM
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!
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...
Rico is my former advisor and I can greatly recommend working with him. Apply by January 4: jobs.uzh.ch/offene-stell...
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...
jobs.uzh.ch
December 11, 2023 at 1:50 PM
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...
Rico is my former advisor and I can greatly recommend working with him. Apply by January 4: jobs.uzh.ch/offene-stell...
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
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 - 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
github.com
November 3, 2023 at 12:50 PM
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
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
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
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
Paper page - Towards Unsupervised Recognition of Semantic Differences in Related
Documents
Join the discussion on this paper page
huggingface.co
October 19, 2023 at 9:59 AM
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
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