Tea Party in the House
A hierarchical probabilistic model combining roll call votes, bill text, and legislative speeches to analyze political …
Machine-Learning
Auto-Encoding Variational Bayes (VAE Paper Summary)
Summary of Kingma & Welling's foundational VAE paper introducing the reparameterization trick and variational …
Importance Weighted Autoencoders: Beyond the Standard VAE
The key difference between multi-sample VAEs and IWAEs: how log-of-averages creates a tighter bound on log-likelihood.
IWAE: Importance Weighted Autoencoders
Summary of Burda, Grosse & Salakhutdinov's ICLR 2016 paper introducing Importance Weighted Autoencoders for tighter …
Recent Advances in the SELFIES Library (2023)
Major updates to the SELFIES library, improved performance, expanded chemistry support, and new customization features.
SELFIES: The Original Paper (Krenn et al. 2020)
The 2020 paper introducing SELFIES, the 100% robust molecular representation that solves SMILES validity problems in ML …
GTR-CoT: Graph Traversal Chain-of-Thought for Molecules
GTR-CoT uses graph traversal chain-of-thought reasoning to improve optical chemical structure recognition accuracy.
SubGrapher: Visual Fingerprinting of Chemical Structures
Novel OCSR method creating molecular fingerprints from images through functional group segmentation for database …
What is Optical Chemical Structure Recognition (OCSR)?
A micro-review of Optical Chemical Structure Recognition (OCSR), covering rule-based systems to modern deep learning …
αExtractor: Chemical Info from Biomedical Literature
αExtractor uses ResNet-Transformer to extract chemical structures from literature images, including noisy and hand-drawn …
MolParser-7M & WildMol: Large-Scale OCSR Datasets
MolParser-7M is the largest OCSR dataset with 7.7M image-text pairs of molecules and E-SMILES, including 400k real-world …
Converting SELFIES Strings to 2D Molecular Images
Visualize SELFIES molecular representations and test their 100% robustness through random sampling experiments.