🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Another lovely meeting of the Maastricht NLP Reading Group (master students, PhDs and UDs). This time we discussed MetaFormer (from Computer Vision) and the simple but powerful pooling i/o self-attention Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭 Abderrahmane Issam UM Department of Advanced Computing Sciences

🤗 Happy summer break from the #MNLP reading group! We will reconvene in September! thales bertaglia Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭 @Khartraxx @antoiloui Haoyang Gui Catalina Goanta

Hey #ACL2023NLP peeps, I will be in Toronto 🇨🇦 open to chat & also presenting 1️⃣ Vendorlink (f/Vageesh Kumar Saxena) ⏰12/Jul 11-1230 x.com/gerasimoss/sta… 2️⃣ Imagination is all you need! (f/Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭): ⏰10/Jul 19-21, 11/Jul 11-1230, 14/Jul 1520-17 (CODI) x.com/gerasimoss/sta…

For the die-hard-still-hungry-for-NLP Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭 is ready to pitch you our work on curved contrastive learning for sequence modelling (short- and long-term dialogue planning). “Imagination is all you need” #CODI2023 #ACL2023NLP #NLProc

intelligence is an emergent property of physics

We are glad to welcome Justus-Jonas Erker (@j_st_s) at UKP Lab, who worked before at the DFKI & Maastricht University 👋 In his PhD, Justus researches representation learning for long-dependency context modeling in dialog systems. You can find him here: erker.ai #NLProc

Many thanks to Florian Mai for an amazing talk at the UKP Lab on Attention alternatives.

Auto-Regressive LLMs have a role to play: turning abstract ideas into token sequences (words, actions, code...). But abstract ideas should be elaborated through planning/reasoning in representation space. AR-LLMs go directly from prompt to answer, skipping the step of reasoning

🚨 Sentence Transformers v2.3.0 has just been released! Sentence Transformers is a framework developed at UKP Lab that allows an easy fine-tuning of custom embeddings models, to achieve maximal performance on your specific task. Release notes: github.com/UKPLab/sentenc…

Attention #NLProc community! 📢 Join the Perspective Argument Retrieval Shared Task, co-located with #argmining_2024 & #ACL2024NLP. Dive into the challenge of retrieving arguments tailored to diverse demographic profiles! 🎨 🚀 blubberli.github.io/perspective-ar… 🗫 perspectivear-zzl7474.slack.com/join/shared_in…

We are happy to announce that 11 papers authored or co-authored by UKP members have been accepted for publication at this year's ACL 2025 in Bangkok 🇹🇭. Congratulations to everyone involved! 💐 #ACL2024NLP 📑 informatik.tu-darmstadt.de/ukp/ukp_home/u… The accepted papers are (1/🧵):

Andreas Waldis HSLU Hochschule Luzern Yufang Hou IBM Research Iryna Gurevych Md. Imbesat Hassan Rizvi Xiaodan Zhu ECE Queens Ingenuity Labs Indraneil Paul Goran Glavaš Universität Würzburg #UniWürzburg Jonibek Mansurov Jinyan Su Artem Shelmanov Akim Tsvigun Osama Afzal Alham Fikri Aji @nyhabash Preslav Nakov MBZUAI TU Darmstadt @IstiCnr NYU Abu Dhabi Furkan Şahinuç Ilia Kuznetsov Irina Bigoulaeva rachneet Harish Tayyar Madabushi BathNLP »Triple-Encoders: Representations That Fire Together, Wire Together« by Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭 (UKP Lab), Florian Mai (Computer Science | KU Leuven), Nils Reimers (cohere), @Gerasimoss Spanakis (Maastricht University) and Iryna Gurevych (9/🧵) #ACL2024NLP 📑 arxiv.org/abs/2402.12332

#acl2024nlp main: Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭 master thesis work UM Department of Advanced Computing Sciences+UKP Lab: Triple-encoders improve contextualization & efficiency without re-encoding, achieving better zero-shot generalization & performance compared to bi-encoders🤖💡 📄: arxiv.org/abs/2402.12332 x.com/UKPLab/status/… >>

Meet our fellow researchers representing UKP Lab at this year's @ACLmeeting: Iryna Gurevych, Qian Ruan, Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭, Indraneil Paul, Fengyu Cai, Sheng Lu, Haishuo, Furkan Şahinuç, Kexin Wang, Haau-Sing Li 李 效丞, Andreas Waldis @EMNLP2024, and a very special guest from BathNLP, @Harish! #ACL2024NLP

Consider following the authors Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭 (UKP Lab), Florian Mai (Computer Science | KU Leuven), Nils Reimers (cohere), @Gerasimoss Spanakis (Maastricht University) and Iryna Gurevych for more information or an exchange of ideas. (8/🧵) See you this week at #ACL2024NLP in Thailand 🇹🇭!

Happening now till 1200 at poster 15! Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭 is eagerly waiting #acl2024nlp

Meet the man who can tell you everything about Triple Encoders: Our colleague Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭 who presented a paper co-authored with Florian Mai (Computer Science | KU Leuven), Nils Reimers (cohere), @Gerasimoss (Maastricht University) and Iryna Gurevych (UKP Lab) at #ACL2024NLP 🇹🇭! x.com/UKPLab/status/…

Eine besondere Auszeichnung: Die TU-Informatikerin Iryna Gurevych Iryna Gurevych erhält als erste Wissenschaftlerin in Deutschland und als erste Universitätsprofessorin den renommierten „Milner Award” der britischen The Royal Society . Herzlichen Glückwunsch! tu-darmstadt.de/universitaet/a…

The Milner Award and Lecture 2025 is awarded to Professor Iryna Gurevych for her major contributions to natural language processing (NLP) and artificial intelligence that combine deep understanding of human language and cognitive faculty with the latest paradigms in machine

We are delighted to share that Iryna Gurevych , the Director of the UKP Lab , has been recognized as one of the 𝗧𝗼𝗽 𝟭𝟬𝟬 𝗺𝗼𝘀𝘁 𝗶𝗻𝗳𝗹𝘂𝗲𝗻𝘁𝗶𝗮𝗹 𝘄𝗼𝗺𝗲𝗻 𝗶𝗻 𝘁𝗵𝗲 𝗚𝗲𝗿𝗺𝗮𝗻 𝗲𝗰𝗼𝗻𝗼𝗺𝘆 by manager magazin and Boston Consulting Group ! 🎉 (1/🧵)