A multidisciplinary, #openaccess journal devoted to the application and development of #machinelearning for the sciences. Published by @IOPPublishing.
Bristol, UK
Joined October 2019
- Tweets5.3K
- Following9.5K
- Followers9.5K
- Likes4.4K
Machine Learning: Science and Technology retweeted
Great article from @TulaneSSE about @mpbquantum's work on optical neural networks!
sse.tulane.edu/speed-light-t…
@Tulane @MLSTjournal
Machine Learning: Science and Technology retweeted
Very excited about our newest paper! "Efficient training for optical computing"
Great job by Manon and Nick:
iopscience.iop.org/article/1…
@Tulane @TulaneSSE @mpbquantum
Machine Learning: Science and Technology retweeted
New paper in @MLSTjournal: task difficulty leaves a clear signature in neural networks, and for harder tasks even simple binarization can collapse performance to chance.
Read more: iopscience.iop.org/article/1…
@filrad @MAngelsSerranoM Marián Boguñá @santo_fortunato
Machine Learning: Science and Technology retweeted
Our paper on machine learning methods for thermometry of simulated Bose–Einstein condensates is now available on IOP @MLSTjournal:
iopscience.iop.org/article/1… – at Ukraine
Machine Learning: Science and Technology retweeted
Our paper is now out in @MLSTjournal, the BEST place for stat mech for ML!
Response theory of first passage processes and the quasi-steady-state hypothesis helps optimize training protocols for neural nets👇@chemistrytau @BioSoftTAU @TelAvivUni
doi.org/10.1088/2632-2153/ad…
Machine Learning: Science and Technology retweeted
My video interview with @QuantaMagazine about AI-designed physics experiments, AI as a Muse for new ideas in Science, and Artificial Scientists: youtube.com/watch?v=T_2ZoMNz…
Machine Learning: Science and Technology retweeted
We show how to estimate the impact of research ideas before they were even born -- just published in @MLSTjournal
[paper] iopscience.iop.org/article/1…
[GitHub]: github.com/artificial-scient…
spearheaded by @GuXuemei
Important for future artificial muses, to generate impactful new ideas.
Machine Learning: Science and Technology retweeted
Our LLM4Mat-Bench paper is now published @MLSTjournal ✨ Test your favorite LLM on the benchmark to predict material properties.
📖Paper: iopscience.iop.org/article/1…
💻Code: github.com/vertaix/LLM4Mat-B…
#NewPaper Have you been wondering how your favorite LLM, e.g. Llama, Mistral, or Gemma performs on materials property prediction? We have just released LLM4Mat-Bench, an extensive benchmark for materials property prediction with LLMs!
LLM4Mat-Bench has unique features:
☀️It spans 10 data collections, containing more than 2.6 Million data points.
☀️It covers 45 distinct material properties.
☀️It covers three different material representations: CIF, text description, and composition.
☀️It provides baseline results from different types and sizes of LLMs, e.g. Llama, Mistral, Gemma, MatBERT, and LLM-Prop.
With materials data scattered everywhere, we believe LLM4Mat-Bench represents a unified data source for driving research on leveraging LLMs for materials science. The benchmark will be maintained and we look forward to your task and data contributions.
Our @andre_niyongabo will present the paper at the AI4Mat #NeurIPS2024 workshop this December.
Paper: arxiv.org/abs/2411.00177
Code: github.com/vertaix/LLM4Mat-B…
Authors: Andre Niyongabo Rubungo (@andre_niyongabo), Kangming Li (@KangmingLi_), Jason Hattrick-Simpers, and Adji Bousso Dieng (@adjiboussodieng)
#AI4Materials #MatSci #NLP4Science #Benchmarks #LLMs #Vertaix
Machine Learning: Science and Technology retweeted
📜Our new paper on detecting quantum vortices with Convolutional Neural Networks has been published in @MLSTjournal!
✅The scheme offers efficient, system-wide vortex detection - even in noisy, experimental data.
🔗 Read here:
iopscience.iop.org/article/1…
#MachineLearning
Machine Learning: Science and Technology retweeted
Paper alert! "New gravitational wave discoveries enabled by machine learning", A. Koloniari, E. Koursoumpa, P. Nousi, P. Lampropoulos, N. Passalis, A. Tefas, N. Stergioulas, doi.org/10.1088/2632-2153/ad… μέσω @MLSTjournal (Open Access)
Machine Learning: Science and Technology retweeted
New paper alert. "Stochastic black-box optimization using multifidelity score function estimator," published in @MLSTjournal (@IOPPublishing ) w\ @mandrakeMojito @SKoutsourelakis prof. Hans Bungartz. iopscience.iop.org/article/1…
#BlackBoxOptimization #SciML #UQ #ML
Machine Learning: Science and Technology retweeted
Our new research article on "Characterizing out-of-distribution generalization of neural networks: application to the disordered SSH model" published in @MLSTjournal by our great student @KacperCybinski led by Prof. A. Dawid @MolecularRobot with @ICFOnians
doi.org/10.1088/2632-2153/ad…
Machine Learning: Science and Technology retweeted
I’m pretty excited about our new paper, which is a follow up to our last paper using AI to help solve a problem in theoretical particle physics. (With Lance, @f_charton, Matthias, Tianji, and @merz_garrett
Machine Learning: Science and Technology retweeted
Link to paper:
arxiv.org/abs/2501.05743
Previous AI/ML paper in @MLSTjournal :
iopscience.iop.org/article/1…
Machine Learning: Science and Technology retweeted
AI predicts that most of the world will warm much faster than previously predicted, according to a new study published today in @ERLjournal. ⏰
Find out more: ow.ly/iSNk50Uo4bL
Machine Learning: Science and Technology retweeted
Now out in @MLSTjournal:
iopscience.iop.org/article/1…
New preprint out today. We study the transferability of both invariant and equivariant neural networks when training these either exclusively on total molecular energies or in combination with data from different atomic partitioning schemes. #compchem
arxiv.org/abs/2409.17575
Machine Learning: Science and Technology retweeted
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @MSFTResearch AI for Science.
#ML #AI #NeuralNetworks #Biology #AI4Science
biorxiv.org/content/10.1101/…
Machine Learning: Science and Technology retweeted
If a clever algorithm finds a super-human solution: What did the machine discover that humans have overlooked?
Happy to have one answer for a super-human quantum optics solution published in @QuantSciTech:
iopscience.iop.org/article/1…
spearheaded by @soerenarlt & @cruizgo_
The super-human solution are experimental designs of high-dimensional GHZ states, discovered by PyTheus (quantum-journal.org/papers/q…). @soerenarlt wanted to know HOW those solutions work. What did the machine find, what's the trick, can we generalize the idea?
Indeed we discovered that PyTheus has generated an effective experimental blueprint for generating multi-photon emitters from just pair sources, by exploiting complex multi-photon interference.
Multiphoton emitters themselves are extremely challenging to build natively. The algorithm has discovered a way to create effective multi-photon emitters, and used it for solving the high-dimensional GHZ question.
Now that we know how to create effective multiphoton emitters, we can use them in many situations, by hand - without the need of algorithms.
It's an example how we humans can learn new physics ideas from a machine. More to come -- for sure!
Machine Learning: Science and Technology retweeted
Two talks at CERN today related to first results using simulation-based inference (likelihood-free inference) at the LHC.
CMS (talk by Calandri): indico.cern.ch/event/1389221…
ATLAS (talk by Gosh): indico.cern.ch/event/1479992…
ATLAS paper: arxiv.org/abs/2412.01600
Machine Learning: Science and Technology retweeted
Exciting research updates from @QSAcenter teams! Researchers led @BerkeleyPhysics published groundbreaking work in the journal @MLSTjournal earlier this year. Access the paper: iopscience.iop.org/article/1…
#QuantumComputing
#ReinforcementLearning
#Innovation
ALT Technical illustration from paper titled: Reinforcement learning pulses for transmon qubit entangling gates