🚨Our Review in Nature just got published on "Designing physics experiments with artificial intelligence" nature.com/articles/s41586-0… Experiments are our way to ask questions to the Universe. Using AI, we have now enormously powerful techniques to find new questions that are too unintuitive and "weird" for humans to find based on their experience and intuition. AI however can explore the space of all possibilities in a completely different way, thus can discover very different solutions. We overview this ability in vastly diverse the fields of physics: quantum optics, light & electron microscopy, gravitational wave physics, high-energy physics, neutrino physics, matter wave physics. For myself this is very special: 12 years after building the first automated design algorithms in quantum experiments, being able to overview the development of the field with my group and friends was an exciting opportunity. Thank you a lot to @PhylomatX for spear-heading this! Thanks a lot to @soerenarlt @cruizgo_ @carlardrguez96 @GuXuemei Philipp Haslinger, @pietrovischia Christian Haack, Yehonathan Drori, @RanaXAdhikari Markus Arndt, Michael Kagan, @lukasheinrich_ for helping developing this Review, bringing insights from so many different directions of physics. So excited about what will happen in the next years! #AI4Science

📢 Super excited: We will organize an @NeurIPSConf Competition -- Learn2Design; with 25,000€ prize money.🤑 💶 A physics experiment design competition for gravitational-wave detectors 🌟 Goal: Develop new optimization & exploration algorithms for extremely complex search spaces in physics. The solutions will likely be immediatly applicable to many questions in the design of new physics experiments -- and will help us to find new questions to the Universe 💫 learn2design2026.com/ Very happy to co-organize this with @PhylomatX , Laurin Sefa, Soham Basu, Priya Kanagasabapathi, @soerenarlt, @GuXuemei , Thomas Christie, Colin Doumont, Andreas Freise, @RanaXAdhikari, Philipp Hennig @uni_tue, Tübingen AI Center, Machine Learning: New Perspectives for Science, @feyerlabs, Friedrich Schiller University Jena, @_nikhef, @Caltech #AI4Science

Very happy that this is out: An analytical, closed-form representation of quantum optics' main source of entanglement -- the two-mode squeezer (TMS) with arbitrary input, and its application to many quantum interference effects. ⚡ Analytical Fock Representation of Two-Mode Squeezing for Quantum Interference arxiv.org/abs/2511.16529 We found new physics interpretations of well-known quantum interference effects, and discovered a new, very strange, multi-particle interference effect that could readily be observed in the laboratory. For us, this is extremely useful, as we will use it as a new, basic representation for our AI-driven projects for discovering new quantum experiments. 🤖 Spearheaded by @GuXuemei , with Carlos Ruiz Gonzalez.

🚨🚨Very excited to share AI-Mandel, our first AI-physicist prototype! AI-Mandel can create new ideas in quantum physics and automatically implement and execute them -- we have already written two papers (on arXiv) based on its recent discoveries! (including a new, never discussed variant of quantum teleportation!) AI-Mandel is a LLM-agent (based on OpenAI's GPT) that creates ideas in natural language and can automatically implement these ideas via access to other, domain-specific AI tools (e.g. PyTheus). The results are natural language idea description, and concrete experimental proposals that can readily be implemented in laboratories. When you run AI-Mandel, it's only task is to find something interesting new in quantum physics, the concrete target is entirely self-generated, and the implementation forces it to define concrete ideas. We think it asks important questions about the creative contributions of human researchers in the scientific process. Spearheaded by @soerenarlt & @GuXuemei at @uni_tue

We show how to estimate the impact of research ideas before they were even born -- just published in @MLSTjournal [paper] iopscience.iop.org/article/1… [GitHub]: github.com/artificial-scient… spearheaded by @GuXuemei Important for future artificial muses, to generate impactful new ideas.

My video interview with @QuantaMagazine about AI-designed physics experiments, AI as a Muse for new ideas in Science, and Artificial Scientists: youtube.com/watch?v=T_2ZoMNz…