🔥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

.Bruce Denby is the author of the very first paper on AI and Particle Physics back in 1988, when he was a post-doc in Orsay ( IJCLab @cnrs_in2p3) working in the CERN LEP DELPHI experiment. He was almost fired for this! #HEPML Tommaso Dorigo Kyle Cranmer Gregor Kasieczka

Alert non-LLM internship position in Zurich Health AI 🍏🚨🧑‍💻 If you 1) have a strong background in deep probabilistic modeling, SBI, hybrid learning or causality 2) are curious about exciting health applications, you should apply! jobs.apple.com/en-il/details/…

Can't recommend enough 👇

Scikit-Learn just crossed 100000 citations! I am no longer part of the core team, but I am proud to have been part of the project since the beginning. A big thank you to all maintainers, contributors, and users for their continuous vision, support and help! 👏 scikit-learn

A huge win for visibility of contributions to science from open source software (often undervalued). It is important to stress that only a few people, who were there in the first few years, are authors of the publication, while many crucial contributors are not.

A thread on quantum interference and the 6 year adventure it took me through In experimental particle physics we sift out events from signal (eg. Higgs) processes vs the orders of magnitude more events from background processes…

This has been such a long time coming… amazing to see this out - Aishik Ghosh led this effort throuout and persevered through this. It also proves that a big ship like ATLAS Experiment can move if you push long enough

A milestone! 10 years ago I had an epiphany about using machine learning to approximate likelihood ratios, enabling statistical inference when your model is a complex simulator. Since then ~1000 papers on SBI have been published, but this is the 1st from the ATLAS Experiment 🧵

After weeks of coding, reviewing and debugging, our GPUs can finally go brrrr! Can't wait to see early results 👀

"Make sure that your model can overfit on small training set" might be the single best sanity check when building ML models. It helped me solve countless implementation errors and to better understand capacity. I first heart it from François Chollet, thanks!

Excited to share the first results using Neural Simulation-Based Inference (NSBI) techniques applied to ATLAS Experiment data! We measure the elusive off-shell Higgs boson with 3.1x better observation sensitivity than standard (histogram) analysis techniques! A thread: (1/N)

The analysis uses more than 10,000 very large NNs (adding upto over 1 billion trainable parameters in total) to build the fully parameterized ratios as a function of more than a 100 parameters. (10/N)

This new framework will extend the vision of the original "Madminer" papers by Kyle Cranmer , Johann Brehmer, Gilles Louppe and others to the LHC use case, potentially enabling wide-scale applications - accelerating discovery potential of the LHC (N/N)

Now in nature, AI Microsoft Research that simulates proteins with more than 10,000 atoms with quantum accuracy, orders of magnitude faster than ever before. AI2BMD's results match those of wet-lab experiments, enabling new biomedical research advances. nature.com/articles/s4158…

Aishik Ghosh is amazing. On top of the latest state of the art in AI/ML and with the tenacity and fearlessness to push this through large particle physics collaboration to get to the real physics impact of some exciting new methods.

This is a first... Reviewer #2 asking us to compare against the very paper we are submitting and that he is (supposed to be) reviewing!? This is all just a farce... #ICLR2025 🙃

A new Science study presents “Evo”—a machine learning model capable of decoding and designing DNA, RNA, and protein sequences, from molecular to genome scale, with unparalleled accuracy. Evo’s ability to predict, generate, and engineer entire genomic sequences could change the

Ciao! 🦋