@_janius_

Prof. "AI for Language Technologies" at @KITKarlsruhe / @KITinformatik

 Karlsruhe, Germany
ai4lt.anthropomatik.kit.edu/english/21_92.php
Joined June 2012
  • Tweets191
  • Following151
  • Followers137
2Media
Jan Niehues retweeted
Sara Papi@sarapapiAug 21
Bittersweet milestone: today is my last day at @FBK_research, wrapping up an incredible 6+ year chapter from my PhD to now! 😢🚀 To cap it off, our paper on streaming SpeechLLMs was accepted to @emnlpmeeting Main! 🎉 📄 Paper: arxiv.org/abs/2605.31432
1
3
37
717
Jan Niehues retweeted
eaclmeeting@eaclmeetingJun 30
📣 #EACL2027 updates: the Call for Papers is live, and our keynote speakers are confirmed! Main conference: 9–14 March 2027. Special theme: The Human in Language. 🧵👇 2027.eacl.org/calls/papers/

Call for Papers

Official website for the 2027 Conference of the European Chapter of the Association for Computational Linguistics

2027.eacl.org
1
21
2
55
16,021
Jan Niehues retweeted
MT Group at FBK@fbk_mtJun 17
We are at the Alliance for Language Technologies - #ALTEDIC Week 2026! @luisabentivogli and @negri_teo are attending two project meetings (ALT-EDIC4EU and #LLMs4EU), presenting the Evaluation of Spoken Language Translation in the context of IWSLT. #LanguageTechnologies #FBK
3
7
163
Jan Niehues retweeted
MT Group at FBK@fbk_mtJun 11
1️⃣ "Do What I Say: A Spoken Prompt Dataset for Instruction-Following" 👥 @MaikeZufle, @sarapapi, Fabian Retkowski, Szymon Mazurek, @mkasztelnik, Alexander Waibel, @luisabentivogli, @_janius_ 🇪🇺 Meetween EU project 📄 arxiv.org/abs/2603.09881

Do What I Say: A Spoken Prompt Dataset for Instruction-Following

Speech Large Language Models (SLLMs) have rapidly expanded, supporting a wide range of tasks. These models are typically evaluated using text prompts, which may not reflect real-world scenarios...

arxiv.org
3
2
101
Jan Niehues retweeted
Sara Papi@sarapapiApr 21
🇧🇷 Heading to 𝗜𝗖𝗟𝗥 2026 to present our paper 𝗠𝗖𝗜𝗙 🚀 The first human-annotated crosslingual multimodal instruction-following benchmark. 🗣️ Drop by the poster if you are interested in Speech AI! Check it out: iclr.cc/virtual/2026/poster/…
1
6
1
24
897
Jan Niehues retweeted
Meetween@MeetweenEUApr 20
Two Meetween papers at #LREC2026 by @MaikeZufle, PhD researcher in instruction-following speech models and full-duplex dialogue at the Karlsruher Institut für Technologie (KIT). 📄 MuSaG 📄 Talk2Ref 👉 lrec2026.info/ #Meetween #NLP
2
5
155
Jan Niehues retweeted
Meetween@MeetweenEUApr 10
4 papers accepted at #LREC -COLING 2026 in Palma de Mallorca 🎉 Sarcasm detection, reference prediction, gender bias in speech translation, and low-resource ASR. Meet the team, 11–16 May 2026 👉 lrec2026.info/ Follow us for paper deep-dives in the coming weeks. #NLP
2
8
157
Jan Niehues retweeted
Matteo Negri@negri_teoMar 2
🚀 Call for Participation: @iwslt Offline Speech Translation 2026 Break language barriers with new languages & real-world scenarios + a brand new source-language agnostic speech translation track 🌍 📅 Evaluation: Apr 1–15 👉 iwslt.org/2026/offline #IWSLT2026 #SpeechAI

Offline ST track

Home of the IWSLT conference and SIGSLT.

iwslt.org
4
6
211
Jan Niehues retweeted
Matteo Negri@negri_teoMar 2
🚀 Call for Participation: @iwslt Subtitling 2026 Turn speech into ready-to-watch subtitles 🎬 across TV, News & YouTube! 📅 Evaluation: Apr 1–15 iwslt.org/2026/subtitling #IWSLT2026 #SpeechAI #MultimodalAI

Subtitling track

Home of the IWSLT conference and SIGSLT.

iwslt.org
7
6
347
Jan Niehues retweeted
Matteo Negri@negri_teoMar 2
🚀 Call for Participation: @iwslt Model Compression 2026 Make large multilingual foundation models small ⚡ without losing power in EN→DE/ZH speech-to-text translation. 📅 Evaluation: Apr 1–15 iwslt.org/2026/compression #IWSLT2026 #SpeechAI #Qwen2 #EfficientAI

Compression track

Home of the IWSLT conference and SIGSLT.

iwslt.org
5
9
316
Jan Niehues retweeted
AI4LT @KIT@Ai4LtFeb 17
📢Fully-funded #PhD position in #NLProc, focusing on #SpeechLLMs & multimodal language processing. Reposts appreciated! 🙏 📅Apply by March 15! 🔗ai4lt.iar.kit.edu/english/te… @_janius_
2
3
173
Jan Niehues retweeted
Sara Papi@sarapapiFeb 10
🚀 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗮𝗿𝘁𝗶𝗰𝗶𝗽𝗮𝘁𝗶𝗼𝗻: @iwslt Instruction Following 2026 Build general-purpose instruction-following speech models for 🌍 EN/DE/IT/ZH languages! 📅 Eval: 𝗔𝗽𝗿 1 | Submit: 𝗔𝗽𝗿 15 👉 iwslt.org/2026/instruction-f… #IWSLT2026 #SpeechAI #MultimodalAI

Instruction Following track

Home of the IWSLT conference and SIGSLT.

iwslt.org
11
13
835
- Preprint: arxiv.org/abs/2502.14429 - Code: github.com/zouharvi/COMET-ea… - Models: huggingface.co/collections/z… Thanks to @MaikeZufle @BeniEgressy @julius_gulius @mrinmayasachan @_janius_ and @EAMTee for sponsoring this research. See you in Rabat for EACL 2026!

Early-Exit and Instant Confidence Translation Quality Estimation

Quality estimation is omnipresent in machine translation, for both evaluation and generation. Unfortunately, quality estimation models are often opaque and computationally expensive, making them...

arxiv.org
1
4
211
Jan Niehues retweeted
Meetween@MeetweenEUJan 29
The Meetween consortium met in Rome for a two-day in-person session hosted by @Translation and @picampusschool. Partners aligned on SpeechLMM progress, roadmap, ethics and next steps toward open, trustworthy speech foundation models. #Meetween #EuropeanAI #OpenSourceAI
2
6
300
Jan Niehues retweeted
DVPS@dvps_aiJan 27
Takeaway from our #2 DVPS consortium meeting: scaling with a few modalities won’t unlock the next leap. Progress we need to push in Europe now requires grounding intelligence in interaction and real-time feedback; we’re working on building the most promising MMFM architecture.
1
3
1
6
269
Jan Niehues retweeted
Sara Papi@sarapapiJan 26
Thrilled to share our paper “MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks” is accepted at @iclr_conf 2026 🎉 🎞️ MCIF is a fully human-annotated, multimodal & cross-lingual IF benchmark. 🔗 Preprint: arxiv.org/abs/2507.19634 #ICLR2026 #AI
6
32
2,266
Jan Niehues retweeted
Meetween@MeetweenEUJan 22
Two years in, Meetween is transforming how we meet. ✅ SpeechLMM v1 released ✅ 560k+ hrs of multilingual speech shared ✅ Global AI benchmarks + ethical design ✅ Built with real users The future of meetings is here, and it's inclusive. #Meetween #AIForGood
2
3
94
Jan Niehues retweeted
Maike Züfle@MaikeZufleJan 14
Join us at the first-ever Speech Translation Metrics Shared Task at IWSLT 2026✨
Vilém Zouhar @ EMNLP@zouharviJan 14
Replying to @zouharvi
Join us and build a model that predicts human annotations of quality based on source speech and its textual translation. iwslt.org/2026/metrics Effort lead by @MaikeZufle , @MarineCarpuat, @h__j___han, @Turchi_Marco, @negri_teo, and others. 🙂

Speech Translation Metrics track

Home of the IWSLT conference and SIGSLT.

iwslt.org
2
3
379
Jan Niehues retweeted
MT Group at FBK@fbk_mt27 Nov 2025
🚀 JOB ALERT2: The FBK's MT Unit is hiring! Join us as a Junior Research Engineer in Multimodal LLMs and help build next-gen AI across text, speech, and video. If you’re passionate about deep learning and multimodal NLP, we want to hear from you! Apply jobs.fbk.eu/Annunci/Jobs_A_J…
10
4
447
Jan Niehues retweeted
Maike Züfle@MaikeZufle3 Nov 2025
I am heading to Suzhou 🌆 for EMNLP, presenting two papers with @f_retkowski, @zouharvi and @TuAnhDinh23. Looking forward to see you at our posters about 🎤Speech Summarization (Fri. Nov 7, 14:00-15:30) and 📊Machine Translation Evaluation (Sat. Nov 8, 11:00-12:00).
1
2
14
563
Load more