Training LLMs end to end is hard. Very excited to share our new blog (book?) that cover the full pipeline: pre-training, post-training and infra. 200+ pages of what worked, what didn’t, and how to make it run reliably
https://t.co/iN2JtWhn23
“Everyone knows” what an autoencoder is… but there's an important complementary picture missing from most introductory material.
In short: we emphasize how autoencoders are implemented—but not always what they represent (and some of the implications of that representation).🧵
Uncertainty is rarely/never exogenous! Certainly not in games when you need to gauge whether your opponent is playing cooperative, min-max, or Nash or… ?!?
📄Paper alert: Strategically Robust Game Theory via Optimal Transport https://t.co/BLb868wbt5
I’m humbled to announce I received the EECI PhD Award for the best PhD thesis in Europe in Systems and Control, for my work at @diis_uz@unizar@i3aunizar. This recognition also belongs to my collaborators, supervisors, and my wife @stepzr for her support and care all these years
To be clear, academia is not inherently "better" or "worse" than industry. In fact, I believe there are amazing opportunities in industry! But, despite its many imperfections, it's hard to find a better option than academia for open-ended curiosity-driven research.
You don't _need_ a PhD (or any qualification) to do almost anything. A PhD is a rare opportunity to grow as an independent thinker in an academic environment, rather than immediately becoming a gear in a corporate agenda. It's definitely not for everyone!
"Floods", by @dev_a_patel, is one of the more astounding Big Data econ papers I have ever seen. Machine learning can be used on satellite data to essentially do magic. How damaging are floods? How much do they affect human capital attainment? A thread on the paper 1/
Calling c the "speed of light" completely misses the point. Rather, c is the "spacetime exchange rate": how many units of space you can exchange for one unit of time.
In actuality, everything travels at the "speed of light", just not necessarily through space alone... (1/4)
Very happy to announce that my PhD student Fan Jiang (@FanOnRobotics) successfully defended yesterday, on "Inertially-Aided Navigation with Ultra-Wideband Wireless Ranging". Fan did some cool work with factor graphs and also built a rust-powered UWB ranging device in the process.