🔥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

Our novel Pix2Code framework is based on program synthesis components and allows to learn readable, revisable and generalisable relational concept representations. Antonia Wüst Quentin Delfosse Devendra Singh Dhami | देवेंद्र सिंह धामी Kristian Kersting #neurosymbolic arxiv.org/pdf/2402.08280…

📢New paper: Ever wondered if LLMs have inherent adversarial capabilities? Short answer: Yes, they have! Our study shows that LLMs can craft adversarial examples to fool classifiers without specifying any explicit perturbation strategy. Paper: arxiv.org/abs/2402.09132

Great day 1 of Elise AI ELISE Wrap Up Conference & ELLIS Community event ✨ Today, Conrad Philipp & Vitus Benson are speakers of workshop “Communicating Al Research to Different Audiences“ 🙌🏻 Also, don’t miss Yoshua Bengio’s key talk!⬇️ shorturl.at/ogj73

Great talk Antonia Wüst . If your interested in learning more about visual concepts via program synthesis check out our poster UAI 2024 tomorrow at 2 PM. paper: arxiv.org/pdf/2402.08280 #UAI2024

#NeuroSymbolic #AI 🤖 enforces constraints, but models can achieve high accuracy using wrong concepts. Can we spot when a model relies on flawed concepts and ensure #trustworthiness? Yes, with BEARS! 🐻 📢 Introducing our latest paper, accepted as a spotlight at UAI2024 !🎉📄

📢 Presenting our latest research on #XAI and Interactive Learning at #ICML2024 🎉 Poster session: Tuesday from 11:30-1:00 (#2604). Title: Learning to Intervene on Concept Bottlenecks 🧠 paper: lnkd.in/eYgka8fj David Steinmann felfri Kristian Kersting

Learning by Self-Explaining (LSX): A Novel Approach to Enhancing AI Generalization and Faithful Model Explanations through Self-Refinement Learning by Self-Explaining (LSX) introduces a novel workflow for enhancing AI model learning, particularly in image classification. It

So happy that our paper Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents (arxiv.org/pdf/2401.05821) has been accepted at NeurIPS 2024! 🎉 If you are wondering why RL agents cannot generalize to new scenarios and how to mitigate it, check it out !

I will be hiring PhD students via ELLIS on multi-objective ML, causal generative models, and fair and interpretable ML. If interested, apply to our probabilistic ML: machinelearning.uni-saarland.de

We have just started our #TANGO_Project 2 day Project Meeting in Paris! Oct 17th-18th, partners will have the opportunity to share the updates and discuss the progress of tasks and expected results of their respective work package. Tune in! #HorizonEurope #HumanCentricAI

Personal update: After 8 amazing years in industry, I will join Computer Science and Engineering at Michigan in fall 2025. I look forward to putting more energy into mentoring, teaching, and collaborating across disciplines and organizations I will look for PhD students this cycle and a postdoc