AI4LT

Last week @ecekt.bsky.social gave a great talk on her recent work "Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models"!

Thank you so much for joining us, Ece! 🌟

聖誕老人究竟如何理解來自世界各地的眾多願望清單上的內容呢？

फादर क्रिसमस वास्तव में दुनिया भर की कई इच्छा-सूचियों पर लिखा हुआ कैसे समझ सकते हैं?

How can Santa actually understand what is written on the many wish lists from all over the world?

Find out at: ai4lt.iar.kit.edu

#kitinformatik #ai4lt #llm #machinelearning #adventskalender #advent

It was great seeing you all at EMNLP in Suzhou. 🤗🌆

I presented two papers, check them out if you are interested in
🎤 Speech (summarization) or
📊 MT evaluation with multiple candidates.

aclanthology.org/2025.emnlp-m...
aclanthology.org/2025.wmt-1.63/

Excited to head over to #Suzhou to present 5 papers at #EMNLP2025 and affiliated venues!
Topics include quality estimation and evaluation 👩‍🔬, speech🗣️, and multilinguality🌐- see you soon! 🤩
@maikezufle.bsky.social @jan-niehues.bsky.social

Let's talk about eval (automatic or human) and multilinguality at #EMNLP in Suzhou! 🇨🇳

- Efficient evaluation (Nov 5, 16:30, poster session 3)
- MT difficulty (Nov 7, 12:30, findings 3)
- COMET-poly (Nov 8, 11:00, WMT)

(DM to meet 🌿 )

Grafik mit zwei Köpfen im Profil gegenüber: Rechts ein angedeutetes Gehirn, im linken Kopf ein Chip mit Leiterbahnen. Dazu der Text: Donnerstag, 30.10.25 18.30 - 20.00 Uhr Stadtbücherei Wörth am Rhein VORTRAG MIT MAIKE ZÜFLE VOM KARLSRUHER INSTITUT FÜR TECHNOLOGIE (KIT) KÜNSTLICHE INTELLIGENZ UND SPRACHE Spannende Einblicke in die Welt der Sprach-KI Eintritt frei Anmeldung erbeten: Tel.: 07271 / 131-225 E-Mail: vhs@woerth.de

Am 30.10.25 lädt die VHS Wörth zu einem spannenden Abend rund um KI und Sprache ein. Maike Züfle, Doktorandin in der Forschungsgruppe Artificial Intelligence for Language Technologies am @kit.edu erklärt, wie große Sprachmodelle Texte verstehen, schreiben und übersetzen u. zeigt praktische Beispiele

At AI4LT we work with AI 🤖 and speech 🎤 every day. But how does Artificial Intelligence actually work – and how can it generate texts and spoken language?
@maikezufle.bsky.social from our group will explain it in a presentation at the Wörth Library📚.

Wir bei AI4LT arbeiten täglich mit 🤖 KI und 🎤 Sprache. Aber wie funktioniert Künstliche Intelligenz eigentlich – und wie kann sie Texte und gesprochene Sprache erzeugen?
@maikezufle.bsky.social aus unserer Gruppe erklärt es in einem Vortrag in der Stadtbücherei #Wörth 📚.
English version below👇

3/3 "Do Slides Help? Multi-modal Context for Automatic Transcription of Conference Talks" led by Supriti

Summarizing Speech: A Comprehensive Survey Speech summarization has become an essential tool for efficiently managing and accessing the growing volume of spoken and audiovisual content. However, despite its increasing importance, speech summar...

2/3 "Summarizing Speech: A Comprehensive Survey" led by Fabian and Maike @maikezufle.bsky.social
arxiv.org/abs/2504.08024

Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability Quality Estimation (QE) is estimating quality of the model output during inference when the ground truth is not available. Deriving output quality from the models' output probability is the most trivi...

1/3 "Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability" led by Tu Anh
arxiv.org/abs/2502.11115

🎉 Starting the week with some great news: 3 of our papers have been accepted to #EMNLP Main! 🧵👇

Big congratulations to all co-authors! 📚✨ Looking forward to presenting in #Suzhou!

Our team is growing! Today, we’re excited to welcome our new colleague Yuka Ko, who joins us as a postdoc on the EU Project DVPS.

Looking forward to collaborating and achieving great things together. Welcome aboard! 🚀

#Interspeech2025 Excited to present our work on in-context language learning for endangered languages! 🤩

Come chat with Zhaolin Li today 14:30–16:30 (A09-P1-04)!

🔗 www.isca-archive.org/interspeech_...

Sara Papi, Maike Z\"ufle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, Jan Niehues
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
https://arxiv.org/abs/2507.19634

Neat year #NLP conferences:
📍 #EACL2026: 24–29 March 🇲🇦 Rabat (ARR deadline: 6 Oct)
📍 #LREC2026: 11–16 May 🇪🇸 Palma de Mallorca (deadline: 17 Oct)
📍 #ACL2026: 2–7 July 🇺🇸 San Diego (ARR deadline: 6 Jan)
📍 #COLING2027: 9–14 May 2027 🇲🇴 Macao

🇦🇹 I’ll be in Vienna for #ACL2025NLP!

Interested in training a speech-aware LLM without a lot of parameteres or data? Come to my poster:
🖼️ Mon, 18:00

Also into Speech Summarization? Join my IWSLT talk in collab with @fbk-mt.bsky.social
🎤 Fri, 14:00

Happy to chat - come say hi! 😎

Papers in 🧵

@jan-niehues.bsky.social @maikezufle.bsky.social

Excited to share 8 papers at #ACL2025 and affiliated venues! 🎉

Our team explored topics including multimodality, cross-lingual transfer, evaluation, decoding, and low-resource languages.

Looking forward to presenting our work and connecting with the community! See you soon! 🤩

🚀 Today marks the official start of the #HorizonEurope DVPS project (dvps.translated.com). Happy that @kit.edu is part of this collaboration with 20 leading AI organizations!

📍 This week we're in Rome for the kickoff meeting. Looking forward to exciting collaborations!
#DVPS #KIT #MultimodalAI

Excited to share 7 papers accepted at #ACL2025 and affiliated venues! 🎉

Topics include multimodality, cross-lingual transfer, benchmarks, decoding, low-resource languages and more.

See you in Vienna! 🤩 #nlproc #acl2025nlp

Program und Lageplan beim Tag der offenen Tür am KIT (Campus Süd) am 17. Mai 2025 #Karlsruhe

Wir freuen uns, bei der diesjährigen #TagDerOffenenTür @kit.edu dabei zu sein! Kommt vorbei und lernt #KITCat, unseren interaktiven KI-Assistenten kennen, und erlebt unser mehrsprachiges Sprachübersetzungssystem in Aktion!

Thrilled to take part in this year's #TagDerOffenenTür @kit.edu!
Come meet #KITCat, our interactive AI assistant, and experience our multilingual speech translation system in action!

@zouharvi.bsky.social and I had fun presenting our poster on efficient reranking for machine translation! Check out our paper with @juliuscheng.bsky.social

aclanthology.org/2025.naacl-l...

📢 One week left to apply for a fully funded 3-year PhD position in our group!

📔Automatic translation with large multimodal models: iecs.unitn.it/education/ad...

📌Full details for application: iecs.unitn.it/education/ad...

📆 Deadline: 12 May 2025, 4pm CEST

#NLProc #FBK

Fabian and I've landed in Albuquerque for #NAACL25🌞 Can’t wait to connect with everyone!

🎤 Talks & 🖼️Posters from @kit.edu on:
- Efficient MT reranking
- Length-controlled summaries
- Cross-modal representations
- Low-resource ASR
- Annotation for qualitative research

🧵👇

Also proud of our collaboration with @juliuscheng.bsky.social and @zouharvi.bsky.social on Bayesian optimization for MT reranking! 🤝 aclanthology.org/2025.naacl-l...

Excited to attend #NAACL in Albuquerque! 🎈🌞
We are presenting works on:

🌐 multilingual & multimodal representations in foundation models aclanthology.org/2025.naacl-s...

🔊 contextual learning for low-resource ASR (LM4UC workshop) aclanthology.org/2025.lm4uc-1.1

We had a great time hosting enthusiastic high schoolers at #GirlsDay2025! We explored #LLM basics, played "Break the AI" games, and shared study abroad opportunities at #KIT.

Thanks @maikezufle.bsky.social for organizing and @kit.edu @girls-day.de for this initiative! 👩‍💻🌟