Danish Khan (@danishk42) 's Twitter Profile
Danish Khan

@danishk42

ID: 1484224989423611905

calendar_today20-01-2022 18:03:30

18 Tweet

43 Followers

65 Following

Anatole von Lilienfeld (@profvlilienfeld) 's Twitter Profile Photo

At chemical accuracy, #QML based on Danish Khan's ultra-compact local many body distribution functionals (MBDF) reaches #QM9 sampling rates of nearly 40 molecules/core second. #QMugs (Kenneth Atz) performance is also promising! With Heini 💉💉💉

At chemical accuracy, #QML based on <a href="/DanishK42/">Danish Khan</a>'s ultra-compact local many body distribution functionals (MBDF) reaches #QM9 sampling rates of nearly 40 molecules/core second. #QMugs (<a href="/atzkenneth/">Kenneth Atz</a>) performance is also promising! With <a href="/Heini_dppf/">Heini 💉💉💉</a>
Anatole von Lilienfeld (@profvlilienfeld) 's Twitter Profile Photo

Adaptive hybrid density functionals cure the spin gap problem in DFT! Optimal HF exchange admixture ratios for specific molecules of arbitrary size and composition, obtained on the fly from amon based #QML models trained across #chemicalspace, result in much improved hybrid DFT

Adaptive hybrid density functionals cure the spin gap problem in DFT! Optimal HF exchange admixture ratios for specific molecules of arbitrary size and composition,  obtained on the fly from amon based #QML models trained across #chemicalspace, result in much improved hybrid DFT
Anatole von Lilienfeld (@profvlilienfeld) 's Twitter Profile Photo

Adaptive atomic basis sets! New preprint live arxiv.org/abs/2404.16942 Amazing work by Danish Khan and Maximilianach! #MachineLearning models of optimal scaling factors render small basis sets more accurate - at negligible overhead. #COMPCHEM #Quantumchemistry #chemicalspace

Adaptive atomic basis sets! New preprint live arxiv.org/abs/2404.16942
Amazing work by <a href="/DanishK42/">Danish Khan</a> and <a href="/maximilianach/">Maximilianach</a>! #MachineLearning  models of optimal scaling factors render small basis sets more accurate - at negligible overhead. #COMPCHEM #Quantumchemistry #chemicalspace
Tim Duignan (@timothyduignan) 's Twitter Profile Photo

It seems we're learning that deep learning is mostly about the data. If you want to know where it will really take off look to areas where you can continuously generate increasingly diverse but consistently high quality data. That leads you to quantum chemistry:

It seems we're learning that deep learning is mostly about the data. If you want to know where it will really take off look to areas where you can continuously generate increasingly diverse but consistently high quality data. That leads you to quantum chemistry:
CCSC2024 (@ccsc2024) 's Twitter Profile Photo

A busy and inspiring week of #chemical #compound space exploration is over! Big thanks to co-organisers, student helpers, speakers, poster presenters, participants, sponsors... and see you in 2 years!

A busy and inspiring week of #chemical #compound space exploration is over! Big thanks to co-organisers, student helpers, speakers, poster presenters, participants, sponsors... and see you in 2 years!
Anatole von Lilienfeld (@profvlilienfeld) 's Twitter Profile Photo

Celebrating the acceptance of our paper introducing machine learning of adaptive hybrid density functionals in Science Advances ! 🥳🥳🥳 We demonstrated that the combination of ideas from functional data analysis with one of the most common approximations in density functional

Celebrating the acceptance of our paper introducing machine learning of adaptive hybrid density functionals in <a href="/ScienceAdvances/">Science Advances</a> ! 🥳🥳🥳 We demonstrated that the combination of ideas from functional data analysis with one of the most common approximations in density functional
Anatole von Lilienfeld (@profvlilienfeld) 's Twitter Profile Photo

With less than 1M compounds, our VQM24 dataset sets a new SOTA in terms of covering more comprehensively the compositional and configurational space of small molecules. Wonderful joint efforts by current and past team-members and collaborators. Hopefully useful for #ML &

With less than 1M compounds, our VQM24 dataset sets a new SOTA in terms of covering more comprehensively the compositional and configurational space of small molecules. Wonderful joint efforts by current and past team-members and collaborators. Hopefully useful for
#ML
&amp;
Anatole von Lilienfeld (@profvlilienfeld) 's Twitter Profile Photo

Dive into the latest from our lab with our newly published article in J Chem Phys! 🌟 @SimonLeonKrug1 and I have been exploring new frontiers in atomistic simulations in terms of universal Alchemical Harmonic Approximation (AHA) based potentials which seamlessly transmutate

Dive into the latest from our lab with our newly published article in J Chem Phys! 🌟 @SimonLeonKrug1  and I have been exploring new frontiers in atomistic simulations in terms of universal Alchemical Harmonic Approximation (AHA) based potentials which seamlessly transmutate
Ash Jogalekar (@curiouswavefn) 's Twitter Profile Photo

Leonard Susskind: "The second law of thermodynamics and statistical mechanics are as deep as the Higgs boson or particle physics." *Whispering*: "Actually they're deeper." "Hope I am not disowned by my particle physics friends." youtube.com/watch?v=D1RzvX…

Jorge Bravo (@bravo_abad) 's Twitter Profile Photo

Refining hybrid density functionals with machine learning to enhance electronic structure predictions Density functional theory has long served as the cornerstone of computational chemistry, offering a balance between accuracy and efficiency in describing molecular and material

Refining hybrid density functionals with machine learning to enhance electronic structure predictions

Density functional theory has long served as the cornerstone of computational chemistry, offering a balance between accuracy and efficiency in describing molecular and material
Anatole von Lilienfeld (@profvlilienfeld) 's Twitter Profile Photo

Super pumped about the prospect of #MachineLearning the adaptive exact exchange admixture in hybrid #DFT approximations: It can even cure the infamous spin-gap problem (see below). Brilliant work out in Science Advances Ilya Kuprov by Danish Khan Alastair Price Bing Huang and Max Ach!

Super pumped about the prospect of #MachineLearning the adaptive exact exchange admixture in hybrid #DFT  approximations: It can even cure the infamous spin-gap problem (see below). Brilliant work out in <a href="/ScienceAdvances/">Science Advances</a> <a href="/Ilya_Kuprov/">Ilya Kuprov</a> by <a href="/DanishK42/">Danish Khan</a> <a href="/Albd90/">Alastair Price</a> Bing Huang and Max Ach!
TCPUniLu (@tcpunilu) 's Twitter Profile Photo

The first part of the ☕️TEA Challenge, featuring Model Analysis, has now also been published in Chemical Science! This concludes the Crash Testing Machine Learning Force Fields TEA Challenge. Congratulations to everyone involved! link: doi.org/10.1039/D4SC06…

The first part of the ☕️TEA Challenge, featuring Model Analysis, has now also been published in <a href="/ChemicalScience/">Chemical Science</a>!

This concludes the Crash Testing Machine Learning Force Fields TEA Challenge. Congratulations to everyone involved!

link: doi.org/10.1039/D4SC06…
CECAM (@cecamevents) 's Twitter Profile Photo

We are already on Day 3 of the workshop "Density Functional Theory and Artificial Intelligence learning from each other" in sunny CECAM-HQ. This afternoon, Fang Liu (Emory University) & Michael Herbst (EPFL) will present their talks.

We are already on Day 3 of the workshop "Density Functional Theory and Artificial Intelligence learning from each other" in sunny CECAM-HQ.
This afternoon, Fang Liu (<a href="/EmoryUniversity/">Emory University</a>) &amp; Michael Herbst (<a href="/EPFL_en/">EPFL</a>) will present their talks.
Danish Khan (@danishk42) 's Twitter Profile Photo

A new non-empirical double hybrid density functional which performs well for general thermochemistry, kinetics and non-covalent tasks while remaining stable for bond dissociations. Please share your thoughts! arxiv.org/abs/2503.22661

A new non-empirical double hybrid density functional which performs well for general thermochemistry, kinetics and non-covalent tasks while remaining stable for bond dissociations. Please share your thoughts!
arxiv.org/abs/2503.22661
Vertaix® (@vertaix_) 's Twitter Profile Photo

#NewPaper Introducing MuAPBEK, a new kinetic energy density functional for quantum chemistry. MuAPBEK has several desirable features. 🐯It is fully analytical: the functional has a closed-form expression and can be optimized for any electronic system via automatic

#NewPaper Introducing MuAPBEK, a new kinetic energy density functional for quantum chemistry. MuAPBEK has several desirable features.   

🐯It is fully analytical: the functional has a closed-form expression and can be optimized for any electronic system via automatic