@Lab_initio

iChem Therefore iAm. Founding Director, Institute for Strategic AI (ISA) | Visiting Researcher @MSFTResearch | Professor of Computational & Materials Chemistry

 NSW, Australia
theisa.ai/
Joined October 2014
  • Tweets2.7K
  • Following473
  • Followers1.4K
244Media
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
Google Scholar is too noisy & lifetime citations bury active momentum. 📉 We built the ISA Academic Profile Engine. 🚀 ✓ Citation Velocity ✓ Impact Filters ✓ Trending Papers Fast, clean & 100% free. Track your momentum here 👇 theisa.ai/academic-profile.h… #AI #ResearchImpact
4
219
We launch the Institute for Strategic AI (ISA) at @UniNewEngland. We link Generative AI and Agentic Workflows directly to physical robotic labs to engineer autonomous discovery loops, accelerating R&D cycle times. theisa.ai #AI #AutonomousSystems #Robotics
2
107
Prof. Amir Karton retweeted
Dozent Tobias
@klein_activistMay 5
Replying to @Lab_initio @MSFTResearch
Finally, a reference dataset large enough to train ML potentials properly. 73k W1-F12 points change what I can model in materials.
1
1
98
“The newly-launched Institute for Strategic AI [UNE] has been using the tech to automate the discovery and testing of potential solvents that can isolate components of the silicon wafers efficiently.”
Renew Economy@renew_economyMay 4
As Australia’s love for #solar threatens to pile into a serious waste stream, researchers are turning to AI to extract more value from retired #panels.. reneweconomy.com.au/aussie-r…

Aussie researchers harness AI to help unlock "cheap, scalable, non-toxic" solar recycling

As Australia's love for solar threatens to pile into a serious waste stream, researchers are turning to AI to extract more value from retired panels.

reneweconomy.com.au
1
1
93
The MSR-ACC/TAE25 database of 73,000 W1-F12 CCSD(T)/CBS atomization energies is now published in Scientific Data! A tremendous collaboration with the @MSFTResearch #AI4Science Team! doi.org/10.1038/s41597-026-0… doi.org/10.5281/zenodo.15387… #CompChem #DeepLearning #DFT #QuantumChemistry
2
6
32
2,203
Prof. Amir Karton retweeted
Orbital Industries
@Orbital_IndApr 23
We're proud to be part of the beta release of @nvidia's ALCHEMI Toolkit. This toolkit is a unified environment for building custom atomistic simulation workflows, built on the same work that powered speedups to Orb-v3, the latest version of our simulation model Orb. Recap from March’s Orb-v3 update: Up to 1.7x faster inference on large systems (up to 100,000 atoms) and up to 33x faster inference on batched small systems with TorchSim support. Our forthcoming OrbMol-v2 model will leverage components from the toolkit including: → PME electrostatics for periodic Coulomb interactions → The MTK integrator for batched constant-pressure molecular dynamics The result: materially lower inference time.
1
5
30
1,891
Prof. Amir Karton retweeted
Stefan Vučković@stefan_theochemApr 23
Very proud of my PhD student @HengZ_921 and joint work with @nagyrpeter and @TCPUniLu: delivering unprecedented DFT accuracy for charged environments (e.g., metalloenzymes). Now in Science Advances: science.org/doi/10.1126/scia… @unifrChemistry

Accurate density functional theory for noncovalent interactions in charged systems

Nonempirical DFT resolves accurate simulation of charged noncovalent interactions.

science.org
3
7
2
46
4,081
Prof. Amir Karton retweeted
Paola Gori-Giorgi@paolagorigiorgiApr 22
The latest release of Skala is out! Accuracy largely improved beyond hybrids at semilocal cost! #compchem
Rianne van den Berg@vdbergrianneApr 22
Today we're sharing a major Skala update: new paper and model release. Skala is a deep-learned XC functional for DFT: 2.8 kcal/mol on GMTKN55, wins 32/55 subsets & surpasses SOTA hybrids in accuracy at semi-local cost. Paper: arxiv.org/abs/2506.14665 Code: github.com/microsoft/skala

Accurate and scalable exchange-correlation with deep learning

Density Functional Theory (DFT) underpins much of modern computational chemistry and materials science. Yet, the reliability of DFT-derived predictions of experimentally measurable properties...

arxiv.org
3
11
1,245
Prof. Amir Karton retweeted
Frank Noe@FrankNoeBerlinApr 22
Skala is now clearly the best DFT functional in the widely accepted community benchmark GMTKN55, and is faster than other high-accuracy functionals. If you're generating DFT data today, go ahead and use it! @MSFTResearch #AI #Science #MachineLearning
Rianne van den Berg@vdbergrianneApr 22
Today we're sharing a major Skala update: new paper and model release. Skala is a deep-learned XC functional for DFT: 2.8 kcal/mol on GMTKN55, wins 32/55 subsets & surpasses SOTA hybrids in accuracy at semi-local cost. Paper: arxiv.org/abs/2506.14665 Code: github.com/microsoft/skala

Accurate and scalable exchange-correlation with deep learning

Density Functional Theory (DFT) underpins much of modern computational chemistry and materials science. Yet, the reliability of DFT-derived predictions of experimentally measurable properties...

arxiv.org
1
7
48
6,778
Prof. Amir Karton retweeted
Mohammed AlQuraishi
@MoAlQuraishiApr 21
Does AlphaFold’s latent space encode only the native state or something like a distribution over conformations? We begin to answer this question with ConforNets, a mechanism for producing diverse states, or very specific ones, via inference-time adaption of OF3p’s latent space👇
Minji Lee@m1nj12Apr 21
We introduce ConforNets, a mechanism for conformational control in AlphaFold3 models - SoTA at producing diverse conformations on every multistate benchmark (N=104) - Novel capability: transfer state from one protein to another Outperforms BioEmu, ConforMix and AFsample3 🧵1/8
3
42
2
219
27,658
Prof. Amir Karton retweeted
Satya Nadella
@satyanadellaApr 23
Thanks to Prime Minister @AlboMP for the warm welcome today. We are making our largest investment in Australia to date, committing A$25 billion to expand AI and cloud capacity, strengthen cybersecurity, and help people and organizations across the country build digital skills.
197
175
57
2,416
179,179
Prof. Amir Karton retweeted
Chin-Wei Huang@chinwei_hApr 22
Exciting new update of Skala. This table should speak for itself: Skala is now the leading density functional in main-group chemistry surpassing previous SOTA hybrid functional at a cheaper, semi-local cost. #compchem #ai4science
Rianne van den Berg@vdbergrianneApr 22
Today we're sharing a major Skala update: new paper and model release. Skala is a deep-learned XC functional for DFT: 2.8 kcal/mol on GMTKN55, wins 32/55 subsets & surpasses SOTA hybrids in accuracy at semi-local cost. Paper: arxiv.org/abs/2506.14665 Code: github.com/microsoft/skala

Accurate and scalable exchange-correlation with deep learning

Density Functional Theory (DFT) underpins much of modern computational chemistry and materials science. Yet, the reliability of DFT-derived predictions of experimentally measurable properties...

arxiv.org
5
16
1,672
I'm thrilled that the new #deeplearning #DFT Skala-1.1 functional is out! arxiv.org/abs/2506.14665 Skala-1.1 breaks the longstanding accuracy-to-cost trade-off of Jacob's Ladder. Amazing collaboration with @paolagorigiorgi and the entire @MSFTResearch AI4Science team! #CompChem
12
1
74
4,212
Prof. Amir Karton retweeted
Rianne van den Berg@vdbergrianneApr 22
Today we're sharing a major Skala update: new paper and model release. Skala is a deep-learned XC functional for DFT: 2.8 kcal/mol on GMTKN55, wins 32/55 subsets & surpasses SOTA hybrids in accuracy at semi-local cost. Paper: arxiv.org/abs/2506.14665 Code: github.com/microsoft/skala

Accurate and scalable exchange-correlation with deep learning

Density Functional Theory (DFT) underpins much of modern computational chemistry and materials science. Yet, the reliability of DFT-derived predictions of experimentally measurable properties...

arxiv.org
3
24
7
97
25,368
Prof. Amir Karton retweeted
Renana Poranne@Aromaticist1 Sep 2025
🎶 If you like it - put a ring on it! 🎵 But... where?? 🤔 Alex's (@awahab_pg) new paper maps the rules of the game for pyrene-based systems! 🥳 From Rings to Properties: Understanding the Effect of Annelation on Pyrene pubs.acs.org/doi/10.1021/acs…

From Rings to Properties: Understanding the Effect of Annelation on Pyrene

Abstract. Pyrene is a central building block in organic materials chemistry, valued for its rigid aromatic core, high fluorescence, and rich capacity for s

pubs.acs.org
1
11
70
2,999
#CompChem + Experiment driving real-world impact! Collaborating with @Joshinano & Nobel Laureate Kostya Novoselov using @NCInews supercomputer, we found calcium ions + graphene oxide can boost atmospheric water harvesting 3×!💧⚙️ tinyurl.com/4eyrsvsd doi.org/10.1073/pnas.2508208…
1
9
333
Prof. Amir Karton retweeted
Kasimir Gregory@kasimirgregory12 Aug 2025
PAHAPS estimates PAH isomer energies from XYZ in seconds. Backed by our JCC study of 38k nonplanar PAHs: ΣDihedral (MAD ~3.6 kcal/mol), +HOMA (~2.5), +fitted xTB (~0.8). Open access: onlinelibrary.wiley.com/doi/… #CompChem #Cheminformatics #PAH @Lab_initio

Big‐Data Analysis of Geometric Descriptors as Efficient Predictors of Energetic Stability in...

Fast, geometry-only descriptors—ΣDihedral, HOMA, and θRMSD—predict isomerization energies for peri-condensed PAHs. The PAH Automated Property Scanner instantly converts an uploaded xyz file into a...

onlinelibrary.wiley.com
1
11
508
Replying to @Aromaticist
Fantastic news! Congratulations @Aromaticist on a well deserved promotion and Happy birthday too! 🎂🎉🎉🎉🎉
1
1
37
The largest snowfall in recorded history really made the @UniNewEngland campus look like Narnia. More photos from the day: labinitio.org/explore/armida… #UNE #Armidale #Snow #Australia
20
831
Yesterday's historic snowfall turned the @UniNewEngland campus into a true winter wonderland. Here are some photos from the incredible day: labinitio.org/explore/armida… #UNE #Armidale #Snow #Australia
1
11
901
Load more