Li Li

李力 Staff ML engineer@Meta ex-ML engineer@YouTube ex-Researcher@GoogleAI Aikido 3rd dan blackbelt Retired Kaggle competition master

[Li Li @leeley18]

My last work at @GoogleAI "Evolving symbolic density functionals" just appeared @ScienceAdvances !Inspired by recent advances in AutoML and program synthesis, we show that ML can compose symbolic density functionals with simplicity as human-designed ones. https://t.co/3JWRMU06CA

[Li Li @leeley18]

@jhrmnn @ja_kirkpatrick @FU_Berlin @bifoldberlin Congratulations!

[Jan Jensen (janhjensen.bsky.social) @janhjensen]

Solving Schrödinger Equation Using Tensor Neural Network https://t.co/Y39GRUYo1Y #compchem

[Andrej Karpathy @karpathy]

Very interesting! A bit like Autopilot but for your computer.

[hardmaru @hardmaru]

Learning with Differentiable Algorithms

If you’re interested in making algorithms differentiable so that algorithms can be learned from training data, @FHKPetersen’s thesis covers differentiable versions of Sorting and Ranking, Top-k, Rendering, Logic.

https://t.co/iP2364uGej

[Li Li @leeley18]

@MilesCranmer This is a nice one

[Xavier (Xavi) Amatriain @xamat]

My friend @jure claims that modern #recsys at most companies are "based on graphical representations" (https://t.co/PqecPmAYGs min.8). In my experience that is not the case. Graphs might be *used*, but are never the fundamental construct. Anyone has similar/different experience?

[Li Li @leeley18]

@tunguz hello :-)

[Andrej Karpathy @karpathy]

Fei-Fei to me after I showed her my first image captioning (image to text) network around 2015: “very cool, now do it backwards!”. Me: “haha that’s impossible” 🥲. Turns out you just need a few ~B alt-text dataset scrape, transformer, diffusion, and a cluster of ~thousand A100s.

[Jürgen Schmidhuber @SchmidhuberAI]

Yesterday @nnaisense released EvoTorch (https://t.co/XAXLH9SDxn), a state-of-the-art evolutionary algorithm library built on @PyTorch, with GPU-acceleration and easy training on huge compute clusters using @raydistributed. (1/2)

[Li Li @leeley18]

@shoyer @DynamicWebPaige Yes! I am glad that it is official. This can unlock a lot of interesting applications!

[Li Li @leeley18]

@tunguz A handcrafted neural network in C++ in @DanielWhiteson numerical computation class project.

[Li Li @leeley18]

@quantumVerd sure thing

[Li Li @leeley18]

@olexandr @rbhar90 Do you mean that geometric deep-learning does not have any advantage over direct deep learning?

[Li Li @leeley18]

A nice article from Dr. Luciano Abriata featuring our recent work on symbolic regression and density functional theory done at @GoogleAI
https://t.co/bzLFd7EntN
#dft #physics #ai4science #ml
Link to our paper "Evolving symbolic density functionals" https://t.co/r9KBQuXtUp

[Li Li @leeley18]

@TheNerdStation what is GCP then?

[Alejandro Piad Morffis @alepiad]

There's a special place in hell for people who code like this:

if condition == True:
return True
else:
return False

Don't be one of those people!

[Li Li @leeley18]

https://t.co/r9qoMjf6gb is your friend

[misha smirnov @SaladZombie]

Talking to a recruiter about a senior data scientist job. I gave her my salary expectation ($150k) and she laughed and told me she’s never seen an offer lower than the 200s. I likely won’t get this job but want to share since no one tells academics these numbers.

[Li Li @leeley18]

@AbhijeetJK Thanks for your interest.

[Li Li @leeley18]

Can computer construct density functionals in the symbolic form?

I would like to share with you our latest work on machine learning applying to density functional theory -- Evolving symbolic density functionals (https://t.co/r9KBQuXtUp)

#SymbolicRegression #ProgramSynthesis
1/3