🎉2 papers accepted to #NAACL2025 Main! All about potential malicious uses of model editing. If a method can effectively modify a model, with anyone able to upload whatever models to Hugging Face or GitHub, we Paul Youssef Christin Seifert @[email protected] Jörg Schlötterer feel it’s a bit scary😅

Day 2 at ICLR 2026, totally overwhelmed 🤯 (in a good way). So much great work, and old friends to Sheffield NLP EngineeringSheffield 🥰 If you're around tomorrow, come check out us 10 AM (Poster Session 5, #296). By ScImage, we're demoing the limits of T2I models.

#ICLR2025 Also, Huge shoutout to my brilliant collaborator Steffen Eger 🙌 🔗 iclr.cc/virtual/2025/p…

Just wrapped up #ICLR2025 and heading to #NAACL2025! I’ll be presenting two papers on detecting model editing: — Oral: Ballroom C, 12:00, April 30 — Poster: May 1, #1618 With so much attention on AI safety at ICLR, these are right on theme. Come say hi! ✨📍🧠 #AISafety #LLMs

🎉 2 accepted to #ACL2025! 🚀 One on multimodality, one on hallucination. Huge thanks to all collaborators and reviewers. This time, I won’t promise “more details coming soon”, still owe that update for the 2 #ICML… 😅But genuinely excited to share more when I can! In the

Great day out in the Peaks for the Sheffield NLP Research Away Day just outside Sheffield! 🚍☕🌲 Inspiring talks, thoughtful discussions, and plenty of time to connect. Thanks to all who joined and made it special!🌺

Heading to #ICML🇨🇦! Had a great time at ACL2023, excited to visit again. I’ll be at Poster Session 6 East (Thu, Jul 17, 16:30) for RULEBREAKER, and Poster Session 2 East (Tue, Jul 15, 16:30) for our position paper on model editing. Perfect timing to grab a drink afterward🍹🍷🥂🍻

📢 3 days left to apply. PhD candidates in computer vision (within ±6 months of graduation) are invited to submit to the BMVC2025 Doctoral Consortium. 📍 In-person at BMVC in Sheffield 🎓 community engagement, research presentation, poster session, more :bmvc2025.bmva.org/calls/doctoral…

Excited to share that 5 papers accepted at #EMNLP2025 (4 main, 1 findings) covering: AIsafety, model editing, compression, text2image, multilingual, in-context learning & fine-tuning. Also my first time seeing an ACL conference in China post-COVID, will be fun🔥Sheffield NLP

New paper by Sam Lewis-Lim et al., to be presented at #EMNLP2025

Two papers accepted @ #AAAI2026 ! 🗣️ Oral: Mitigating Content Effects on Reasoning in LMs via Fine-Grained Activation Steering 🖼️ Poster: Making Visual Dialogue More Engaging – A New Task, Method & Metric Huge thanks to all collaborators 🍻😊