iiinova — where your digital self keeps evolving

Reposted by Angelika Romanou

Badr AlKhamissi @bkhmsi.bsky.social · 07/01/2026

🎉 Re-Align is back for its 4th edition at ICLR 2026! 📣 We invite submissions on representational alignment, spanning ML, Neuroscience, CogSci, and related fields. 📝 Tracks: Short (≤5p), Long (≤10p), Challenge (blog) ⏰ Deadline: Feb 5, 2026 for papers 🔗 representational-alignment.github.io/2026/

1169 16

Reposted by Angelika Romanou

Negar Foroutan @negarforoutan.bsky.social · 15/12/2025

1/ 🌍 How does mixing data from hundreds of languages affect LLM training? In our new paper "Revisiting Multilingual Data Mixtures in Language Model Pretraining" we revisit core assumptions about multilinguality using 1.1B-3B models trained on up to 400 languages. 🧵👇

196 9

Reposted by Angelika Romanou

MELT Workshop @meltworkshop.bsky.social · 10/10/2025

Keynote talk: Apertus: Democratizing Open and Compliant LLMs for Global Language Environments. Imanol Schlag introduces Apertus, a fully open suite of LLMs with a focus on compliance, transparency, and multilingual representation training across 1000+ languages. 🌍🤖

031 3

Reposted by Angelika Romanou

Deniz Bayazit @bayazitdeniz.bsky.social · 25/09/2025

1/🚨 New preprint How do #LLMs’ inner features change as they train? Using #crosscoders + a new causal metric, we map when features appear, strengthen, or fade across checkpoints—opening a new lens on training dynamics beyond loss curves & benchmarks. #interpretability

2156 15

Angelika Romanou @agromanou.bsky.social · 12/09/2025

Proud to have been part of the team behind #Apertus 🌍✨ an open multilingual LLM. Trained on open data, supporting 1,800+ languages, and built with transparency, compliance & responsible AI in mind. 🤖 Try Apertus models: huggingface.co/collections/...

huggingface.co

Apertus LLM - a swiss-ai Collection

Democratizing Open and Compliant LLMs for Global Language Environments: 8B and 70B open-data open-weights models, multilingual in >1000 languages

020 2

Angelika Romanou @agromanou.bsky.social · 23/04/2025

If you’re at @iclr-conf.bsky.social this week, come check out our spotlight poster INCLUDE during the Thursday 3:00–5:30pm session! I will be there to chat about all things multilingual & multicultural evaluation. Feel free to reach out anytime during the conference. I’d love to connect!

042 4

Reposted by Angelika Romanou

silingao.bsky.social @silingao.bsky.social · 01/04/2025

NEW PAPER ALERT: Generating visual narratives to illustrate textual stories remains an open challenge, due to the lack of knowledge to constrain faithful and self-consistent generations. Our #CVPR2025 paper proposes a new benchmark, VinaBench, to address this challenge.

165 6

Reposted by Angelika Romanou

Antoine Bosselut @abosselut.bsky.social · 25/02/2025

Lots of great news out of the EPFL NLP lab these last few weeks. We'll be at @iclr-conf.bsky.social and @naaclmeeting.bsky.social in April / May to present some of our work in training dynamics, model representations, reasoning, and AI democratization. Come chat with us during the conference!

12512 25

Reposted by Angelika Romanou

Badr AlKhamissi @bkhmsi.bsky.social · 19/12/2024

🚨 New Paper! Can neuroscience localizers uncover brain-like functional specializations in LLMs? 🧠🤖 Yes! We analyzed 18 LLMs and found units mirroring the brain's language, theory of mind, and multiple demand networks! w/ @gretatuckute.bsky.social, @abosselut.bsky.social, @mschrimpf.bsky.social 🧵👇

210325 103

Reposted by Angelika Romanou

Sepideh Mamooler@ACL🇦🇹 @smamooler.bsky.social · 17/12/2024

🚀 Introducing PICLe: a framework for in-context named-entity detection (NED) using pseudo-annotated demonstrations. 🎯 No human labeling needed—yet it outperforms few-shot learning with human annotations! #AI #NLProc #LLMs #ICL #NER

1128 12

Angelika Romanou @agromanou.bsky.social · 05/12/2024

Introducing Global-MMLU🌍: A multilingual benchmark featuring MMLU translations in 42 languages crafted with: ✅ Human curation ✅ Extensive metadata ✅ Insights into cultural sensitivity Proud to have collaborated with Shivalika Singh, @sarahooker.bsky.social and Cohere For AI!

0134 13

Reposted by Angelika Romanou

Antoine Bosselut @abosselut.bsky.social · 04/12/2024

1/ 📘 Could ChatGPT get an engineering degree? Spoiler, yes! In our new @pnas.org article, we explore how AI assistants like GPT-4 perform in STEM university courses — and on average they pass a staggering 91.7% of core courses. 🧵 #AI #HigherEd #STEM #LLMs #NLProc

13614 36

Angelika Romanou @agromanou.bsky.social · 02/12/2024

👏 As well as the fantastic multilingual research community that helped us collect and validate INCLUDE!

030 3

Angelika Romanou @agromanou.bsky.social · 02/12/2024

🙏 We thank our amazing core team and advisors: @negarforoutan.bsky.social, Anna Sotnikova, @eric-zemingchen.bsky.social, Sree Harsha Nelaturu, Shivalika Singh, Rishabh Maheshwary, Micol Altomare, Mohamed A Haggag, Imanol Schlag, @mziizm.bsky.social, @sarahooker.bsky.social, @abosselut.bsky.social

140 4

Angelika Romanou @agromanou.bsky.social · 02/12/2024

For easy evaluation, we provide the following subsets: INCLUDE-base: up to 550 samples per language, totaling ~23K questions 🤗 : huggingface.co/datasets/Coh... INCLUDE-lite: up to 250 samples per language, totaling ~11K questions 🤗 : huggingface.co/datasets/Coh...

150 5

Angelika Romanou @agromanou.bsky.social · 02/12/2024

🤝 Information is transferred across languages of the same script, though untrained languages might also excel due to potential data contamination. 🌎 Models can struggle with non-English instructions, entangling knowledge evaluation with other factors such as task formatting.

130 3

Angelika Romanou @agromanou.bsky.social · 02/12/2024

Analysis shows: 📚 Models have a long way to go in capturing the regional knowledge reflected in languages. 💪 Model scale improves regional knowledge understanding, but other techniques like CoT or instruction tuning have minimal or negative impacts.

130 3

Angelika Romanou @agromanou.bsky.social · 02/12/2024

To build INCLUDE, we collected ~200K MCQ data from 44 languages and 58 knowledge domains, collected from local sources in 52 countries, representing a rich array of cultural and regional knowledge.

161 6

Angelika Romanou @agromanou.bsky.social · 02/12/2024

🤔 Why is regional knowledge so important? Users expect #LLMs to know information relevant to their environments— customs, culture, etc. To be relevant & relatable, LLMs need to know these nuances. It's not just global knowledge; it's about meeting user needs where they are.

141 4

Angelika Romanou @agromanou.bsky.social · 02/12/2024

🌍 First, what is regional knowledge? It's the local info, culture & practices of a regional context. US Law is a great topic, but not as relevant for multilingual LLMs for other regions. For INCLUDE, we collect regional knowledge rather than translating Western-centric benchmarks.

140 4

Angelika Romanou @agromanou.bsky.social · 02/12/2024

🚀 Introducing INCLUDE 🌍: A multilingual LLM evaluation benchmark spanning 44 languages! Contains *newly-collected* data, prioritizing *regional knowledge*. Setting the stage for truly global AI evaluation. Ready to see how your model measures up? #AI #Multilingual #LLM #NLProc

1396 39

Reposted by Angelika Romanou

Antoine Bosselut @abosselut.bsky.social · 26/11/2024

.@icepfl.bsky.social is hiring for multiple positions in CS (including one open call): www.epfl.ch/about/workin... Apply to come join us in Beautiful Lausanne!

epfl.ch

Open Faculty Positions

0129 12