MagNET predicts NMR in seconds as an ML surrogate for DFT calculations

CatAstro_Piyush · x · 2026-07-23

A collaboration involving Merck and academic researchers launched MagNET, an ML surrogate for DFT-based NMR calculations.

• The model predicts NMR with good accuracy in seconds, instead of running expensive quantum chemistry workflows.
• The chart compares MagNET-Zero against older and newer baselines across geometry sources and basis sets, showing lower RMSE at much lower computation time.
• The image frames the result as a practical speedup over conventional DFT NMR pipelines.

Original post →

More from Research

• Nature paper images cellular activity across all organs, revealing body-wide circuits — arjunrajlab · 2026-09-11
• SignNet 1M Dataset Released for Sign Language Research — ducha_aiki · 2026-09-11
• ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
• InFlux++ Method Released — ducha_aiki · 2026-09-11
• Skyfall GS Uses Flux to Refine Gaussian Splatting, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11
• Could 10k agents discover learning methods beyond backprop, or just tweak existing ones? — SeunghyunSEO7 · 2026-09-11

Research channel →