Grateful to have Michael as a labmate/collaborator! Check out his work In 2nd year of PhD, I struggled to find a long-term direction. When he joined our group, his wild ideas led us to the frontier of causality + large-scale medical data. PhD has been smooth sailing ever since😀

Congrats Elias Bareinboim! Very excited about this direction

Are you more likely to meet somebody different from you in a big city or in a small town? Check out our new paper in nature. We refute the myth that cities are cosmopolitan melting pots, finding extreme segregation in big cities. nature.com/articles/s4158… segregation.stanford.edu

Come join me and Michael Moor @ NeurIPS. Today at 5:15pm in Great Hall & Hall B1+B2 (level 1) #2001 Presenting our spotlight poster on zero-shot causal learning: personalized treatment effect prediction when the treatment is novel and has never been seen before.

We had a splendid poster session yesterday! Thanks for stopping by and the great discussions! 🤩 Loved how one person who went: "Zero-shot? That's impossible!🤯" #NeurIPS2023 Hamed Nilforoshan

Can deep learning work on small data with far more features than samples? We present PLATO: a method that achieves the state-of-the-art on such datasets by using prior domain information! neurips.cc/virtual/2022/p… 🧵 Published in #NeurIPS2023 with Hongyu Ren @kexinhuang5 Jure Leskovec

Wonderful podcast by Alicia Curth @AleksanderMolak Completely agree that in Causal ML we are rich in methods but poor in understanding. We need more analysis, benchmarks, and applications to real-world data.

Best advice I received from Neil Shah at Snap Research (CMU PhD): “In research, progress is a step function. For months things it will appear as if there is no progress before a breakthrough happens. That’s just part of the game. You cannot change it. But you can pick 1-2

We solved a problem previously thought by chemists to be impossible: reconstructing precise chrystal structures from X-ray diffraction patterns. Super proud of this Stanford-MIT collaboration with my best friend Eric Riesel as the lead. news.mit.edu/2024/ai-model-…