🔥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

Activation functions reduce the topological complexity of data. Best AF may be diff for diff models and diff layers, but most Transformer models use GELU. What if the model learns optimized activation functions during training? led by Haishuo with Ji Ung Lee and Iryna Gurevych

Super excited to have a second paper at #ACL2023NLP !!🎉 In this paper, we propose a new method to teach NLP in a more interactive way using SQuARE Project Super happy to contribute to improving NLP teaching :)

Are Emergent Abilities in Large Language Models just In-Context Learning? Spoiler: YES 🤯 Through a series of over 1,000 experiments, we provide compelling evidence: arxiv.org/abs/2309.01809 Our results allay safety concerns regarding latent hazardous abilities. A🧵👇 #NLProc

Next, Bayes! 😎 Edwin Simpson’s talk: Efficiently Acquiring Human Feedback with Bayesian Deep Learning

Furkan Şahinuç Ilia Kuznetsov Yufang Hou IBM Research Iryna Gurevych Irina Bigoulaeva rachneet Harish Tayyar Madabushi BathNLP Justus-Jonas Erker 🇪🇺 @ ACL2024 🇹🇭 Computer Science | KU Leuven Nils Reimers cohere Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social Maastricht University Max Glockner Preslav Nakov MBZUAI Qian Ruan Kexin Wang Jan-Christoph Klie Juan Haladjian »DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs« by Haishuo (UKP Lab), Xiaodan Zhu (ECE Queens / Ingenuity Labs) & Iryna Gurevych (15/🧵) #ACL2024NLP 📑 arxiv.org/abs/2406.07080

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

1/12 📢New paper alert “DOCE: Finding the Sweet Spot for Execution-Based Code Generation” The work is a group effort with Patrick Fernandes, Iryna Gurevych, and Andre Martins. UKP Lab ELLIS Unit Lisbon DeepSPIN 📰: arxiv.org/pdf/2408.13745