**How can we tell if a video is AI generated?** 👉 new paper: arxiv.org/abs/2507.00583 As scientists, we want to know if video models actually learned the laws of physics 🌍 As users, we want to make sure that we can trust and know when something is real 🏛️

🚨 We’re thrilled to announce our NeurIPS 2025 workshop: CausCien: Uncovering Causality in Science 🔍✨ We’re uniting ML + science communities to explore how causal learning advances: 🌿 Ecology 🧬 Biology 📊 Social Science & more! 📝 Submit by Aug 22 👉 sites.google.com/view/causcien

In the past 2 years, we are seeing sparks of enlightenment shining from even strongest citadels of "experimental design" literature. In 2017, the editors of the Journal of the American Medical Association (JAMA) wrote that when evaluating a submission, they would “verify whether

Simplifying my life to focus on doing truly impactful work, one day at a time.

Exploratory causal inference in SAEnce: a new unsupervised approach to discover causal effects in exploratory scientific experiments. Co-led by tommaso mencattini and Riccardo Cadei

Your paper sounds very interesting in its scope, but I must confess that I cannot appreciate its findings, primarily because you focus on the methods rather the input-output problems. What is given and what kind of question are you trying to answer. I suggest you write an

Judea Pearl Treatment Effect estimation requires priors defining candidate effects. Without priors there are not ‘computable causal claims’, i.e., what is the treatment affecting, in the sense of maximal causal abstraction with semantic interpretation? Example: what is the effect of a

🚀 Excited to share LinEAS, our new activation steering method accepted at NeurIPS 2025! It approximates optimal transport maps e2e to precisely guide 🧭 activations achieving finer control 🎚️ with ✨ less than 32 ✨ prompts! 💻github.com/apple/ml-lineas 📄arxiv.org/abs/2503.10679