12 posts tagged with machine-learning.
Summary of Liu et al.'s ICLR 2025 paper introducing DenoiseVAE, a novel pre-training framework that learns molecule-adaptive and atom-specific noise …
Summary of Bigi et al.'s 2025 paper that critically evaluates the trend of using non-conservative force models in atomistic machine learning, …
Summary of Lu et al.'s 2025 paper introducing SpaceFormer, a Transformer-based framework that models the entire 3D space around a molecule—not just …
Summary of Dai et al.'s NeurIPS 2021 paper introducing Noise Contrastive Priors (NCPs), a novel method using noise contrastive estimation to train …
A comprehensive dataset card for the MoleculAR Conformer Ensemble Learning (MARCEL) benchmark - the first comprehensive benchmark for learning from …
A comprehensive dataset card for the Geometric Ensemble Of Molecules (GEOM) dataset - 37 million energy-annotated molecular conformations for machine …
Summary of Weiler et al.'s 3D Steerable CNNs paper from NeurIPS 2018, which introduces SE(3)-equivariant convolutional networks for volumetric data …
Introduces the TABME++ benchmark and evaluates LLM performance on page stream segmentation, demonstrating superior performance of decoder-based models …
VAE tutorial using modern PyTorch: torch.distributions, optimization techniques, numerical stability, and implementation patterns.
Build ML models to classify congressional bills by policy area. Analysis of TF-IDF features with Naive Bayes, Logistic Regression, and XGBoost.
Build GROMACS workflows for simulating mini-proteins across multiple amino acids. Generate diverse MD trajectories for machine learning.
Machine learning models to classify congressional bills by policy area, achieving 87%+ accuracy through systematic analysis of legislative text and …