TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

research

One GPU Painted Missing Baryons in Minutes

BIND learned field-level gas, star and dark-matter structure across a 35-dimensional simulation space.

Published Updated Story ID: mp-2026-09-12-014
Read the complete editionStory JSON

Summary

BIND learned field-level gas, star and dark-matter structure across a 35-dimensional simulation space.

Weak-lensing forecasts need the way gas and stars reshape matter, but full hydrodynamic simulations are expensive. BIND learns to map dark-matter-only halos to dark matter, gas and stellar fields using 1,024 paired CAMELS simulations spanning cosmology and galaxy-formation parameters. The authors report percent-level mass recovery, radial profiles within roughly 10%, and preserved shape and residual relationships without giving the model halo mass as an input. Applied halo by halo to a 512-cubed-particle volume, it reproduced projected power suppression in minutes on one GPU.

Why it matters

BIND learned field-level gas, star and dark-matter structure across a 35-dimensional simulation space.

Limits and context

  • BIND learns to map dark-matter-only halos to dark matter, gas and stellar fields using 1,024 paired CAMELS simulations spanning cosmology and galaxy-formation parameters.

Key claims

  1. BIND learned field-level gas, star and dark-matter structure across a 35-dimensional simulation space.

    Qualification: BIND learns to map dark-matter-only halos to dark matter, gas and stellar fields using 1,024 paired CAMELS simulations spanning cosmology and galaxy-formation parameters.

    Evidence: source-2026-09-12-014

Sources

  1. arXiv preprint 2609.10709arXiv · primary research

Corrections

No corrections have been recorded for this story.