News
Researchers Use AI to Accelerate Superconductor Discovery
2+ hour, 11+ min ago (727+ words) An **Aalto-led Super C** team reported on June 29, 2026 that machine-learning-guided screening helped identify and experimentally confirm two kagome superconductors, **YRu3 B2** and **Lu Ru3 B2**. The Physical Review Research paper reports superconducting critical temperatures of **0. 81 K and 0. 95 K**, so this is not a room-temperature…...
GLACIER integrates multimodal student-teacher model for molecular prediction
3+ week, 5+ day ago (735+ words) Per the ar Xiv paper (ar Xiv: 2606. 11382), **GLACIER** is a multimodal student-teacher foundation model for molecular property prediction that combines molecular graphs, SMILES strings, and physicochemical descriptors. Per the paper, the framework pretrains three student encoders on **100, 000** drug-like molecules: a message-passing…...
Paper surveys model-agnostic signal discovery methods
1+ mon, 6+ day ago (376+ words) The ar Xiv entry **ar Xiv: 2605. 31103**, submitted on **29 May 2026**, presents a review titled "Model-Agnostic Signal Discovery with Machine Learning: Bridging the Gap Between Theory and Practice," with authors listed on the submission page including **Oz Amram** and two others, according to…...
Physics-Informed AI Maps Glymphatic Fluid Velocity
1+ mon, 1+ week ago (777+ words) A multidisciplinary team led by Professor Douglas Kelley at the University of Rochester used physics-informed neural networks to infer brain-wide glymphatic fluid velocities from MRI tracer videos, according to a University of Rochester press release and coverage in Neuroscience News…...
ML molecular dynamics models phase separation in Si-C-N ceramics
1+ mon, 2+ week ago (689+ words) The ar Xiv preprint 2605. 20358 by Fabien Mortier et al. presents a machine-learning interatomic potential for **silicon carbonitride (Si-C-N-H)** systems and applies it to large-scale molecular dynamics. The authors report training the potential on a diversified database of over **9000 configurations**, per…...
SINAPSE introduces lightweight explainable neutron-gamma discrimination
1+ mon, 3+ week ago (598+ words) According to the ar Xiv submission 2605. 13627 (submitted 13 May 2026), Thomas Carreau et al. present **SINAPSE**, a lightweight deep learning framework for neutron-gamma discrimination in **organic scintillators**. The paper reports a dual-branch architecture that pairs a **1-dimensional convolutional autoencoder** for waveform denoising…...
Study uses protein-design experiments to refine energy functions
2+ mon, 2+ week ago (100+ words) The paper directly links experimental protein-design data to energy-function development, offering practical accuracy gains for modeling and protein engineering; it is a notable research advance rather than a paradigm shift. Practice interview problems based on real data 1, 500+ SQL & Python problems…...