🚀 Introducing a novel approach for controllable object-centric learning! By conditioning on language descriptions, we unlock targeted object-language binding in complex scenes—no mask supervision needed! Here's how it works 👇 🧵 #NeurIPS2024

Want to train a *multilingual* LVLM but not sure how? Or looking for a strong model to use? Presenting "Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model"! Arxiv: arxiv.org/abs/2501.05122 HF Collection: huggingface.co/collections/Wu…

⚠️Struggling with multilingual news recommendation? We introduce NaSE, a news-adapted sentence encoder!🙌 ✅No costly fine-tuning needed ✅Perfect for cold-start & few-shot scenarios #ecir2025 📰: arxiv.org/abs/2406.12634 Try it out Hugging Face🤗: huggingface.co/aiana94/NaSE 👇

Excited to present today a poster at OECD ➡️ Better Policies for Better Lives in Paris International Association for Safe & Ethical AI based on our upcoming paper "Societal Alignment Frameworks Can Improve LLM Alignment" (stay tuned for the pre-print soon! 🎊). Today (Fri) at 1pm CET. Conference livestream: iaseai.org/conference

Presenting ✨ 𝐂𝐇𝐀𝐒𝐄: 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐢𝐧𝐠 𝐬𝐲𝐧𝐭𝐡𝐞𝐭𝐢𝐜 𝐝𝐚𝐭𝐚 𝐟𝐨𝐫 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 ✨ Work w/ fantastic advisors 🇺🇦 Dzmitry Bahdanau and Siva Reddy Thread 🧵:

The 6th AfricaNLP Workshop will be co-located with ACL 2025 in Vienna, Austria, on the theme: "Multilingual and Multicultural-aware LLMs" sites.google.com/view/africanlp… Submission deadline: March 7, 2025. We accept both archival and non-archival papers. #AfricaNLP Masakhane

Agents like OpenAI Operator can solve complex computer tasks, but what happens when users use them to cause harm, e.g. automate hate speech and spread misinformation? To find out, we introduce SafeArena (safearena.github.io), a benchmark to assess the capabilities of web

Excited to invite you to submit and join our CVPR 2025 workshop on geo-diverse and culturally aware vision-language models! 🌍✨ Let’s push the boundaries of AI together. #CVPR2025

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories We are releasing the first benchmark to evaluate how well automatic evaluators, such as LLM judges, can evaluate web agent trajectories. We find that rule-based evals underreport success rates, and

On my way to #NAACL2025 ✈️ I'll present the paper on Friday (May 2) 9-10:30am at poster session 7. Happy to chat about any aspect of multilingualism and culture! I'm also open to postdoc and visiting positions in the US. Definitely reach out if you have any opportunities.

📢 Call for Papers is out!📢 Working on #news #recsys & their societal, legal, and ethical dimensions? 👉Submit to the 13th INRA, co-located w/ ACM RecSys in Prague! 📅 Paper deadline: ** July 17th, 2025 ** More info: research.idi.ntnu.no/NewsTech/INRA/… #INRA2025 #RecSys2025

🏆 Our paper has received the Outstanding Paper Award at NAACL HLT 2025! 🎉 Many thanks to my co-authors Katharina von der Wense and Anne Lauscher (she/her)! We introduce Multi3Hate, a novel multimodal and multilingual parallel hate speech dataset annotated by a multicultural set of annotators.

📢 Introducing Walk&Retrieve, a simple yet effective zero-shot #RAG framework based on #knowledgegraph walks! Arxiv : arxiv.org/abs/2505.16849 GitHub: github.com/MartinBoecklin… Joint work w/ Martin Böckling Heiko Paulheim Data and Web Science Group IR-RAG #SIGIR2025 Details 👇