🔥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

Ever wondered which jailbreak attack offers the best bang for your buck?🤖 Check out our #NeurIPS2024 workshop paper on a realistic threat model for LLM jailbreaks! We introduce a threat model that considers both fluency and compute efficiency for fair attack comparisons. 🧵 1/n

Wow, I'm honored to receive a NeurIPS travel award by WiML for my poster! Big shoutout to the great Tuebingen WiML🦋 team who organized the amazing workshop here in Tübingen 🥳

Researching #AI #ComputerVision #MachineLearning #Robotics #HCI? Join our elite doctoral program - a partnership with MPI-IS, @uni_stuttgart & Universität Tübingen! Applications accepted until Nov 15, 2024 at imprs.is.mpg.de/application

Anyone interested in part-time/remote marketing at Parameter Lab & researchtrend.ai? We're looking for someone with AI knowledge and experience in tweeting and content creation.

Im September hat Sarah unsere Unterrichtsplattform 🥝 kiwi.schule auf dem Workshop "KI-Bildung 2024" im Rahmen der DELFI-Tagung 2024 der #GI vorgestellt. Mehr dazu könnt ihr in unserem Paper (doi.org/10.18420/delfi…) nachlesen.

My last week as Apple intern was insane. 3 paper deadlines? Sure, I can do it. "Wanna interview this week?" Sure, I can! "Wanna present your side project to the senior VP?" Sure, I... wait 🤯 I had such a flow! It was so fun! I want more. I'm joining Apple as a Research Scientist

Thrilled to share our NeurIPS spotlight on uncertainty disentanglement! ✨ We study how well existing methods disentangle different sources of uncertainty, like epistemic and aleatoric. 🧵👇 1/7 📖: arxiv.org/abs/2402.19460 💻: github.com/bmucsanyi/unta…

On my way to Vancouver for NeurIPS Conference and the ATTRIB workshop on 14th! Feel free to drop by ✨ If you're also interested in data attribution or human-centered XAI, let me know and I'd be happy to meet :)

At NeurIPS? Check out the 2nd workshop on Attributing Model Behavior at Scale (ATTRIB)! Meeting Rm 205-207, starting @ 9am - amazing talks from Surbhi Goel Sanmi Koyejo Baharan Mirzasoleiman, Robert Geirhos, and Seong Joon Oh + exciting contributed talks! More info: attrib-workshop.cc

Giving a talk tomorrow at #NeurIPS2024!

I will be in ATTRIB workshop tomorrow (attrib-workshop.cc). Stop by if you’d like to chat with me and connect with other great researchers in this area.

Today, I'm giving a talk on Continual Foundation Model Learning at the Adaptive Foundation Models workshop NeurIPS Conference (adaptive-foundation-models.org) 🏠1 PM at Exhibit Hall A If you're interested in continual pretraining, flexible benchmarking, and more, please stop by!

Happening now!

Our first talk of the day @ ATTRIB 2024 (Rm 205-207): Surbhi Goel on attributing model behavior using synthetic data!

Next up, Sanmi Koyejo on predicting downstream properties of language models!

Sanmi Koyejo After some amazing contributed talks, we now have a panel moderated by Sadhika Malladi - with Seong Joon Oh Baharan Mirzasoleiman and Robert Geirhos!

Sanmi Koyejo Sadhika Malladi Seong Joon Oh Baharan Mirzasoleiman One great poster session (and lunch) later - Baharan Mirzasoleiman on data selection for large language models!

Sanmi Koyejo Sadhika Malladi Seong Joon Oh Baharan Mirzasoleiman Our second-last talk of the day - Robert Geirhos on “how do we make attribution easy?”

Sanmi Koyejo Sadhika Malladi Seong Joon Oh Baharan Mirzasoleiman After another very lively poster session, our final talk of the day from Seong Joon Oh - who is talking about the interactions between ML, attribution, and humans!

+++Startschuss für KI macht Schule Austria+++ Diesen Juli: KI macht Schule Austria gegründet! 🚀 Mit ersten Workshops in Wien, Salzburg und Innsbruck bringen wir KI-Bildung in Österreichs Schulen. 🏫🧑‍🏫 Mehr dazu: ki-macht-schule.at & sn.at/salzburg/polit…