AM-IA brings together news, research papers and applications relating to artificial intelligence published around the world into a single feed — and makes them available in your European language at the click of a button.
Scroll to browse · Click to filter
Variation autoencoders on diffuse background spectra show that six latent variables are sufficient, as well as in the standard cosmological model.
Three researchers compared quantum, hybrid and classical models on simulated Sangria data from the future space gravitational wave observatory.
Tested on the 18th release of data from the Sloan Digital Sky Survey, this unsupervised model competes with conventional methods: 0.46% outliers on good quality spectra.
Applied to RadioAstron and ALMA archives, the method is scaled to the number of pixels and provides more statistical information than the conventional CLEAN algorithm.
After three weeks of commissioning, the prototype equipped with four TPUs communicates with the ground. Constraint of energy forces, only one chip can turn, about twenty minutes in a row.
Rather than looking for the rarest object, researchers ask a vision-language model what is scientifically interesting. Cost: about $5 per 10,000 images.
In a virtual reality simulation, 16 participants manipulated an arm mounted on rover with joystick or look. The second mode is much faster and less tiring, but less precise for removal.
Without dedicated training, tabular foundation models estimate the shift to photometric red better than tools designed for, from only 1,000 reference galaxies.
More than 3,800 sources detected, located and recorded by neuron networks, with comparable or better results than the official chain when the galactic emission model varies.
To link astronomical observations to language, AstroBridge automatically matches data and passages from scientific articles. The model obtained increased the distinction between quasars and galaxies from 69% to 91.5%.
A problem that has remained without an analytical solution for three centuries: researchers train a network on N-body simulations and then extract legible formulae that beat existing estimates.
Pre-trained on cheap FastPM simulations and then refined on a small batch of high fidelity CAMELS simulations, a network needs only 5 to 15% of them to achieve the same accuracy.
On 120 tablets already dated, the system places the published year at the top of its ranking in 96% of cases, and proposes candidate dates for 56 undated texts so far.
Beyond the simple mention, the tool classifies the actual use of an observatory's data over six levels. It reaches 89.1% accuracy and is already operating at China's national astronomical data centre.
A simulation of a constellation of about one million computing satellites shows that it would contaminate on average 20% of LSST poses over a year, and would multiply by more than ten the brightness of the sky at dusk.
Researchers cut the problem into two levels so that a swarm of vessels can carry a rigid object in a fuel-efficient manner.
For the ESC instrument of the 3-metre telescope funded by Eric and Wendy Schmidt, two astronomers draw up an initial list of planets of ages and temperatures never observed in direct imaging.
An open test bench simulates the capture of floating objects and maintenance tasks inspired by the ISS: a generalistic model captures only 6 targets out of 400.
Tested on 10,497 confirmed transients, the Fritz production module recovers 83% of non-taxonomy objects by inspecting only 15% of the flow.
Out of 500 questions from 346 astronomy articles, five models reach nearly 90% of the right answers in easy versions, but cap around 60% as soon as the authors' explanation is only partial.